© 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. 39884
    Prev
    Next
    INDEX
    Explanations

    code files

    np_max-act-logits · gemini-2.0-flash
    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
     sublic
    -0.34
    3
    -0.33
    .githubusercontent
    -0.32
    RequiredMixin
    -0.30
    leness
    -0.29
    æĹıèĩªæ²»åİ¿
    -0.29
    warz
    -0.28
    lez
    -0.28
     hamburg
    -0.28
    isers
    -0.27
    POSITIVE LOGITS
     Rec
    0.33
     Mot
    0.32
     ")
    0.32
     Ana
    0.32
     Me
    0.32
     Maur
    0.31
     Motor
    0.31
     ""
    0.31
     Comp
    0.30
     Bet
    0.30
    Activations Density 43.090%

    No Known Activations