© 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. 17540
    Prev
    Next
    INDEX
    Explanations

    column values and data

    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
    cape
    -0.12
    ness
    -0.09
    tings
    -0.09
    orbit
    -0.09
    ult
    -0.09
    heet
    -0.08
    utan
    -0.08
    fully
    -0.08
     pace
    -0.08
    -0.08
    POSITIVE LOGITS
    nect
    0.13
    aires
    0.11
    iseum
    0.11
     trá»Ŀi
    0.10
    amarin
    0.10
    arity
    0.10
    ophon
    0.10
    ãģ¹ãģį
    0.10
    NECT
    0.10
     ë¶Ī구íķĺê³ł
    0.10
    Activations Density 0.059%

    No Known Activations