© 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. 23-TRANSCODER-HP
    7. 24992
    Prev
    Next
    INDEX
    Explanations

    something

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¿Ļ个éĹ®é¢ĺ
    -0.25
     RAT
    -0.25
     hab
    -0.25
    çļĦè¶ĭåĬ¿
    -0.24
     Recommendations
    -0.24
     Pages
    -0.23
    oping
    -0.23
    lingen
    -0.23
     Likes
    -0.23
    æľĢåIJĪéĢĤ
    -0.23
    POSITIVE LOGITS
    å¤ĸ
    0.28
    åĨĽåĽ¢
    0.27
    EmailAddress
    0.25
    .cloudflare
    0.25
    inputEmail
    0.24
    éķ£
    0.24
    æł¡å¤ĸ
    0.24
    æĬ«
    0.24
    bery
    0.24
     plc
    0.23
    Activations Density 0.000%

    No Known Activations