© 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. 29743
    Prev
    Next
    INDEX
    Explanations

    French names

    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
     cir
    -0.30
     prob
    -0.27
     aim
    -0.27
    -db
    -0.26
    éĺİ
    -0.26
    atest
    -0.25
    éĢı
    -0.25
    opal
    -0.24
     gang
    -0.24
     combination
    -0.24
    POSITIVE LOGITS
    etty
    0.26
     ngũ
    0.25
    æīĵå¾Ĺ
    0.25
    ึà¸ĩ
    0.25
    anus
    0.24
    裳
    0.24
    çĥŃå¿ĥ
    0.24
    usk
    0.23
     enthus
    0.23
    AxisSize
    0.23
    Activations Density 0.917%

    No Known Activations