© 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. 23043
    Prev
    Next
    INDEX
    Explanations

    mon

    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
    acman
    -0.26
    ature
    -0.26
    客æ°Ķ
    -0.25
    DataContract
    -0.24
    thouse
    -0.24
    ystone
    -0.24
    ×Ļ׾
    -0.24
    ocese
    -0.23
     groom
    -0.23
     ram
    -0.23
    POSITIVE LOGITS
    ç´ł
    0.32
    ãĤµãĤ¤
    0.28
    à¹Ĥà¸ĭ
    0.25
    쪽
    0.25
    inity
    0.25
    ãĥIJãĥ¼
    0.25
     Exhibit
    0.24
    第äºĮèĬĤ
    0.24
    åİŁæĸĩåľ°åĿĢ
    0.24
    ulist
    0.24
    Activations Density 0.002%

    No Known Activations