© 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. 31-TRANSCODER-HP
    7. 18325
    Prev
    Next
    INDEX
    Explanations

    academic/technical texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    formatter
    -0.28
    åĪĨåŃIJ
    -0.28
    ucher
    -0.27
    hetto
    -0.27
    enal
    -0.26
    HO
    -0.26
    å®ģ
    -0.24
    breaker
    -0.24
     Synthetic
    -0.24
     amat
    -0.23
    POSITIVE LOGITS
     qualified
    0.29
     taxonomy
    0.27
     qualify
    0.26
    æĦıåIJij
    0.25
    ħ§
    0.25
    å¥Ĺ
    0.25
    è´¨æ£Ģ
    0.24
     mats
    0.24
    æīĵåĮħ
    0.24
    eds
    0.24
    Activations Density 0.822%

    No Known Activations