© 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. 149550
    Prev
    Next
    INDEX
    Explanations

    prior

    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
    æĸ¹éĿ¢
    -0.29
    ç»Ŀ对
    -0.27
     buurt
    -0.25
    äºĽ
    -0.25
    ienia
    -0.25
    åı¤ä»Ĭ
    -0.25
    è´µ
    -0.25
    容
    -0.24
    尽头
    -0.24
     aspect
    -0.24
    POSITIVE LOGITS
     Sisters
    0.27
     completion
    0.26
    åĬŁè¯¾
    0.25
    Woman
    0.25
    çĤ¹äºĨ
    0.25
    Maker
    0.24
     Silence
    0.24
    åıĹçIJĨ
    0.24
    éªijè¡Į
    0.23
    itional
    0.23
    Activations Density 0.241%

    No Known Activations