© 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. 3930
    Prev
    Next
    INDEX
    Explanations

    PL, L, l variations

    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
    est
    -0.19
    ìľ¼ë¡ľ
    -0.16
    el
    -0.16
    ed
    -0.15
    es
    -0.15
    els
    -0.14
    land
    -0.13
    ely
    -0.13
    ening
    -0.13
    eam
    -0.13
    POSITIVE LOGITS
    icious
    0.19
    ambda
    0.17
    ationship
    0.16
    ibrary
    0.15
    anguage
    0.15
    ty
    0.15
    mente
    0.15
    dehyde
    0.15
    ipsis
    0.15
    istic
    0.15
    Activations Density 2.503%

    No Known Activations