© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 23505
    Prev
    Next
    INDEX
    Explanations

    Code/software

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    å¥
    -0.26
    athe
    -0.26
    PTY
    -0.26
     Ethiopian
    -0.25
    .Api
    -0.25
     иÑģкÑĥÑģ
    -0.25
     attract
    -0.25
    å¸Ĥåľºä¸Ĭ
    -0.25
    æĶ¯ä»ĺ
    -0.24
     appeals
    -0.24
    POSITIVE LOGITS
    .unregister
    0.28
    Readable
    0.26
     sz
    0.26
    ãģĶ
    0.26
    unist
    0.25
    mer
    0.25
    remen
    0.24
    ersions
    0.24
    人åĬĽ
    0.24
    Week
    0.24
    Activations Density 0.001%

    No Known Activations