© 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. 25385
    Prev
    Next
    INDEX
    Explanations

    religious texts

    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
    Dec
    -0.28
     yet
    -0.28
    å¢
    -0.28
     indeed
    -0.27
    ice
    -0.27
    wald
    -0.26
     very
    -0.26
     unlike
    -0.26
     even
    -0.26
     dec
    -0.26
    POSITIVE LOGITS
     SHALL
    0.25
    åħ¬æĬ¥
    0.25
    ä¹ĭ称
    0.25
    alley
    0.25
    uids
    0.25
    åĩºèº«
    0.24
    è¶Ĭ好
    0.24
    ëĵĿ
    0.24
    éĢļæĬ¥
    0.23
    å¿ĥå¢ĥ
    0.23
    Activations Density 0.004%

    No Known Activations