© 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. 9-TRANSCODER-HP
    7. 29801
    Prev
    Next
    INDEX
    Explanations

    being overwhelmed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é³Į
    -0.30
    çĵ¦
    -0.27
    ulfilled
    -0.26
     filled
    -0.26
     dime
    -0.26
     finely
    -0.25
     wall
    -0.24
     satur
    -0.24
    irim
    -0.24
    è
    -0.24
    POSITIVE LOGITS
    IRST
    0.28
    çĶ·
    0.27
    åŁºæľ¬æĥħåĨµ
    0.26
    plr
    0.26
    第ä¸Ģ个
    0.26
    .Tasks
    0.25
    好å¥ĩå¿ĥ
    0.25
    女çĶŁ
    0.25
    åĽ½åĢº
    0.25
    irst
    0.24
    Activations Density 1.819%

    No Known Activations