© 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. 95351
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     escal
    -0.31
    rium
    -0.26
    åľ¨éĤ£éĩĮ
    -0.26
    çĭĢ
    -0.25
    ima
    -0.24
    ä¹ĭæĥħ
    -0.24
    uably
    -0.24
    жа
    -0.23
    ography
    -0.23
    积累
    -0.23
    POSITIVE LOGITS
    entai
    0.26
    //=
    0.26
     NOI
    0.25
    angen
    0.25
     intimate
    0.25
    SHARE
    0.24
    anker
    0.24
    xcd
    0.24
    tör
    0.23
     gén
    0.23
    Activations Density 0.882%

    No Known Activations

    This feature has no known activations.