© 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. 150969
    Prev
    Next
    INDEX
    Explanations

    the

    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
    smarty
    -0.27
     inquiries
    -0.27
    ingen
    -0.25
     BASIC
    -0.25
     enquiries
    -0.25
    asi
    -0.25
     favourite
    -0.24
    unnable
    -0.24
    åĭĸ
    -0.24
    ud
    -0.24
    POSITIVE LOGITS
    è¿Ļ座
    0.28
    åıijå±ķ壮大
    0.25
    æĭ±
    0.24
     shoulders
    0.24
    tec
    0.24
    è£ī
    0.24
    éľĩèį¡
    0.23
    廨
    0.23
    èĢ½è¯¯
    0.23
    ãĦĸ
    0.23
    Activations Density 0.899%

    No Known Activations