© 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. 31-TRANSCODER-HP
    7. 18233
    Prev
    Next
    INDEX
    Explanations

    iron

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    warm
    -0.26
    ç»ĵæŀĦè°ĥæķ´
    -0.25
    ç´¢
    -0.25
    vro
    -0.25
     ally
    -0.24
    vvm
    -0.24
    æ¼ıæ°´
    -0.24
    è·£
    -0.24
    VML
    -0.23
    İ·
    -0.23
    POSITIVE LOGITS
    æģ¨
    0.27
    anan
    0.25
    osos
    0.25
    çĽĺ
    0.25
    ENT
    0.25
     QByteArray
    0.24
    -cookie
    0.24
    åįĬ天
    0.24
    Ent
    0.24
    ple
    0.24
    Activations Density 0.142%

    No Known Activations