© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 24-TRANSCODER-HP
    7. 149526
    Prev
    Next
    INDEX
    Explanations

    comma/quote

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     necessary
    -0.28
     proport
    -0.25
    æĸ°äº¬
    -0.25
    ä¸ij
    -0.24
     taught
    -0.24
     literal
    -0.24
     ```
    -0.24
    å¿ħè¦ģçļĦ
    -0.24
     needed
    -0.24
    ths
    -0.24
    POSITIVE LOGITS
     davon
    0.27
    è§Ĩ线
    0.27
     scissors
    0.25
    /chart
    0.25
    ÅĤe
    0.24
    /rand
    0.24
    è¿Ļä¸Ģ天
    0.24
     Lac
    0.24
    READING
    0.24
    chez
    0.23
    Activations Density 1.148%

    No Known Activations