© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 57907
    Prev
    Next
    INDEX
    Explanations

    Copyright notices with names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ull
    -0.11
    yard
    -0.10
    PerPage
    -0.10
     phá»ij
    -0.10
    ark
    -0.10
    ror
    -0.10
    Ñĩа
    -0.10
    èĥĸåŃIJ
    -0.10
    çĢijå¸ĥ
    -0.10
    è´«åĽ°äººåı£
    -0.10
    POSITIVE LOGITS
    centage
    0.16
    entially
    0.15
    egasus
    0.14
    ICTURE
    0.13
    formance
    0.13
    folio
    0.12
    seudo
    0.12
    thag
    0.12
    ï¬ĥ
    0.12
     darn
    0.12
    Activations Density 2.761%

    No Known Activations