© 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. 24-TRANSCODER-HP
    7. 150087
    Prev
    Next
    INDEX
    Explanations

    Code and technical information

    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
    已达
    -0.28
    å·²ç»ıè¾¾åĪ°
    -0.27
    aux
    -0.26
    å·²æĪIJ为
    -0.26
     PROP
    -0.25
    ะ
    -0.25
    æĿ¥æºIJäºİ
    -0.24
    æĪŁ
    -0.24
    æľįåĬ¡äºİ
    -0.24
    ä¸įä¿¡
    -0.24
    POSITIVE LOGITS
    .onerror
    0.26
    ese
    0.26
    enson
    0.25
    æķ´åIJĪ
    0.25
     ensure
    0.25
    elow
    0.24
    Ñĥгл
    0.24
    Composer
    0.24
    /epl
    0.24
    etak
    0.24
    Activations Density 2.345%

    No Known Activations