© 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. 20-TRANSCODER-HP
    7. 141275
    Prev
    Next
    INDEX
    Explanations

    news/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asan
    -0.28
     unloaded
    -0.27
    stoff
    -0.25
    åı¦è¡Į
    -0.25
    ibo
    -0.25
    å£ģ
    -0.25
    eso
    -0.25
    å§Ķ
    -0.24
    æĺ¾çİ°
    -0.24
    çĦ¶æĺ¯
    -0.24
    POSITIVE LOGITS
     Fine
    0.28
    ä¸Ģåı£æ°Ķ
    0.25
    fine
    0.25
    ç»Ĩ
    0.24
     fine
    0.24
    Fine
    0.24
     Pros
    0.24
     OMIT
    0.24
    gles
    0.24
     Valid
    0.23
    Activations Density 52.024%

    No Known Activations