© 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. 29664
    Prev
    Next
    INDEX
    Explanations

    code/technical writing

    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
    hap
    -0.26
    .writeInt
    -0.25
     autom
    -0.25
    ela
    -0.25
     ST
    -0.24
    tega
    -0.24
    ×Ļ×ŀ×ķת
    -0.23
    iles
    -0.23
    èĽ±
    -0.23
    æĮ¯å¥ĭ
    -0.23
    POSITIVE LOGITS
    /browser
    0.27
    çĺħ
    0.27
    alık
    0.26
    ernals
    0.26
     Parliamentary
    0.26
    .future
    0.26
     clearfix
    0.25
    空çĻ½
    0.24
    éĥ½è¯´
    0.24
    verity
    0.24
    Activations Density 1.141%

    No Known Activations