© 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. 23213
    Prev
    Next
    INDEX
    Explanations

    African countries and/or questions

    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
    iph
    -0.29
    ä¿Ŀå¯Ĩ
    -0.28
    åľ°éģĵ
    -0.28
    å¸ĮæľĽèĥ½
    -0.26
     denial
    -0.26
     pharm
    -0.26
    icon
    -0.25
    wish
    -0.24
    康çĨĻ
    -0.24
    å¸ĮæľĽèĥ½å¤Ł
    -0.24
    POSITIVE LOGITS
    asting
    0.29
     Instruments
    0.26
    Literal
    0.25
     Literature
    0.25
    encias
    0.24
    als
    0.24
     Sadd
    0.24
    èµį
    0.24
    aways
    0.24
    chwitz
    0.23
    Activations Density 0.000%

    No Known Activations