© 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. 24-TRANSCODER-HP
    7. 151088
    Prev
    Next
    INDEX
    Explanations

    clauses

    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
    place
    -0.26
     AND
    -0.24
    çĥŁåĽ±
    -0.24
    );\↵
    -0.24
    .RunWith
    -0.24
    istics
    -0.24
     cap
    -0.23
    orea
    -0.23
    _feed
    -0.23
    é«ĺæķĪ
    -0.23
    POSITIVE LOGITS
    etta
    0.32
    elope
    0.25
    çŃĶæ¡Ī
    0.25
    请éĹ®
    0.25
    稽
    0.25
    (AP
    0.25
    peaker
    0.24
     appro
    0.24
    æĬ±æŃī
    0.24
    çļĦçŃĶæ¡Ī
    0.23
    Activations Density 0.116%

    No Known Activations