© 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. 150005
    Prev
    Next
    INDEX
    Explanations

    catch-all text

    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
    è½®
    -0.27
    å¼Ĭ
    -0.27
    éªij
    -0.25
    -so
    -0.25
     Occasionally
    -0.24
     Fry
    -0.24
    天天
    -0.24
    éªijåħµ
    -0.24
     Cycling
    -0.23
    AMED
    -0.23
    POSITIVE LOGITS
    RequestBody
    0.26
    etical
    0.25
    å¾ĭ
    0.25
    客æµģ
    0.25
    ICLES
    0.24
    峤
    0.24
    ä¾Ŀæ³ķ追究
    0.24
    _DISPLAY
    0.24
    áºŃt
    0.24
    æľ¬èº«å°±
    0.24
    Activations Density 0.162%

    No Known Activations