© 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. 12-TRANSCODER-HP
    7. 22809
    Prev
    Next
    INDEX
    Explanations

    Finding or needing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸ĢéĿ¢
    -0.28
    -faced
    -0.28
    éļ¾
    -0.27
    éªĸ
    -0.26
    GM
    -0.25
    quences
    -0.25
     closest
    -0.24
    nqu
    -0.24
     Gunn
    -0.24
    plen
    -0.23
    POSITIVE LOGITS
    arp
    0.28
     domic
    0.25
    çĵ¦
    0.25
     Rogue
    0.24
    eenth
    0.24
    adro
    0.24
    worm
    0.23
    atile
    0.23
    åķı
    0.23
    ç¢Į
    0.23
    Activations Density 0.000%

    No Known Activations