© 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. 22857
    Prev
    Next
    INDEX
    Explanations

    descriptive texts

    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
     деле
    -0.26
    巨人
    -0.25
    rectangle
    -0.25
     Rectangle
    -0.24
    å½±åĥı
    -0.24
    è¶ĬæĿ¥è¶Ĭ大
    -0.24
    æĸŃè£Ĥ
    -0.24
    ylon
    -0.24
    åħĥå·¦åı³
    -0.23
    æīĩ
    -0.23
    POSITIVE LOGITS
    æĺ¯å¯¹
    0.27
    arked
    0.26
     preval
    0.26
    è¿ĻäºĽéĹ®é¢ĺ
    0.26
    ÑĢед
    0.25
    æ¦Ĥè¿°
    0.25
     Tang
    0.25
    oko
    0.24
    atitude
    0.24
    olarity
    0.24
    Activations Density 0.003%

    No Known Activations