© 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. 30-TRANSCODER-HP
    7. 95707
    Prev
    Next
    INDEX
    Explanations

    load

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ska
    -0.30
    inel
    -0.29
    egov
    -0.27
    VERS
    -0.27
     ÐĿи
    -0.26
     Builds
    -0.25
    kin
    -0.24
     cá»Ń
    -0.24
    æIJ¬è¿ģ
    -0.24
     outfits
    -0.24
    POSITIVE LOGITS
     connected
    0.34
     associated
    0.34
    ces
    0.30
     prevail
    0.29
    cas
    0.29
     connection
    0.28
     whether
    0.28
     on
    0.27
     accessory
    0.27
     fo
    0.27
    Activations Density 0.024%

    No Known Activations