© 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. 150818
    Prev
    Next
    INDEX
    Explanations

    Quantities in recipes

    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
     thụ
    -0.28
    ApiController
    -0.27
    éĢļ
    -0.27
     traverse
    -0.27
    çĶŁæ´»
    -0.26
     ashamed
    -0.25
    æĭ´
    -0.25
    illo
    -0.25
     travers
    -0.24
     lifestyle
    -0.24
    POSITIVE LOGITS
    éļĨéĩį
    0.26
    orney
    0.25
    ç«ĭãģ¦
    0.25
    ERIC
    0.25
     оÑĩеÑĢедÑĮ
    0.24
     ALOG
    0.24
     pinch
    0.24
    è½®
    0.24
    _MINOR
    0.24
     grocery
    0.24
    Activations Density 0.110%

    No Known Activations