© 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. 150246
    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
    atar
    -0.28
    夸大
    -0.28
    åŃ¥
    -0.27
    rouw
    -0.25
    rador
    -0.24
     folk
    -0.24
    compan
    -0.24
    loor
    -0.24
     getContext
    -0.24
    åī¯åİ¿éķ¿
    -0.24
    POSITIVE LOGITS
    .annot
    0.26
     hút
    0.25
    Enumer
    0.24
    å½ĵäºĭ
    0.24
    ä¹ĭå¤ľ
    0.24
    _executor
    0.24
    é¼¾
    0.23
    åīįèĢħ
    0.23
    ç»ĨåĪĻ
    0.23
    讽
    0.23
    Activations Density 0.011%

    No Known Activations

    This feature has no known activations.