© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 18-TRANSCODER-HP
    7. 89102
    Prev
    Next
    INDEX
    Explanations

    Organizations and Institutions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     foss
    -0.27
    etty
    -0.27
    ala
    -0.26
     grad
    -0.26
    NetMessage
    -0.25
     Regents
    -0.25
    è³ĵ
    -0.25
    instead
    -0.24
    errs
    -0.24
    -panel
    -0.24
    POSITIVE LOGITS
    berger
    0.28
    çļĦçľ¼ç¥ŀ
    0.27
    ãĤĭãĤĤãģ®
    0.27
    æĭĵ
    0.26
    ONO
    0.25
     ----------------------------------------------------------------------------↵
    0.25
    ilight
    0.24
    æľīéĹ®é¢ĺ
    0.24
    æľīè¿ĩ
    0.24
    åł¡
    0.24
    Activations Density 6.116%

    No Known Activations