© 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. 35-TRANSCODER-HP
    7. 40213
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .googleapis
    -0.26
    æĺ¾èijĹ
    -0.26
    elic
    -0.26
    jom
    -0.25
     honored
    -0.25
    atas
    -0.25
    åį³æŶ
    -0.25
    produk
    -0.25
     thanked
    -0.25
     praised
    -0.25
    POSITIVE LOGITS
     Worst
    0.31
    (Const
    0.29
    оÑĤ
    0.28
     Hot
    0.27
     Need
    0.27
     Hard
    0.26
    ìĥģ
    0.26
     hÃłnh
    0.26
    Ñĥд
    0.25
     Sud
    0.25
    Activations Density 2.051%

    No Known Activations

    This feature has no known activations.