© 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. 150794
    Prev
    Next
    INDEX
    Explanations

    code snippets and data

    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
     flush
    -0.30
     wh
    -0.28
    isters
    -0.25
     minor
    -0.25
    çī¹éķ¿
    -0.25
    reten
    -0.24
    trap
    -0.24
    ä¸ĩäºĭ
    -0.24
     polynomial
    -0.24
     politic
    -0.24
    POSITIVE LOGITS
    æİĩ
    0.31
    éĵī
    0.27
    âĸ¼
    0.26
    æĦĽ
    0.26
    ÑĮÑİ
    0.26
    asser
    0.25
    agrid
    0.25
     latina
    0.24
     divide
    0.24
    divider
    0.24
    Activations Density 0.096%

    No Known Activations