© 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. 23765
    Prev
    Next
    INDEX
    Explanations

    Capac

    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
    -length
    -0.30
    -Length
    -0.28
     Russians
    -0.27
     dint
    -0.27
     particulars
    -0.26
     jÄĻzyk
    -0.26
    éĻ¢éķ¿
    -0.25
    coverage
    -0.25
    ENCES
    -0.24
    è·ijäºĨ
    -0.24
    POSITIVE LOGITS
    è§Ĵèī²
    0.36
     roles
    0.35
     role
    0.34
    èģĮèĥ½
    0.31
    role
    0.31
    _role
    0.30
    Role
    0.29
    çļĦè§Ĵèī²
    0.29
    uesta
    0.29
    omic
    0.28
    Activations Density 0.003%

    No Known Activations