© 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. 149691
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    å°±æĺ¯è¿Ļæł·
    -0.28
    æĶ¶
    -0.27
    undry
    -0.27
     WARRANTIES
    -0.25
     unlock
    -0.24
    ä¸ĬåѦ
    -0.24
    elivery
    -0.24
    .schedulers
    -0.24
    ×ķ×Ļ×ķת
    -0.24
    rang
    -0.24
    POSITIVE LOGITS
     Plan
    0.28
    _plan
    0.28
    Plan
    0.28
     based
    0.27
     plan
    0.27
    asi
    0.26
    é¾Ħ
    0.24
    æ¼Ķ
    0.24
    åŁºäºİ
    0.24
     Position
    0.24
    Activations Density 0.018%

    No Known Activations

    This feature has no known activations.