© 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. 49464
    Prev
    Next
    INDEX
    Explanations

    commentary by

    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
    ened
    -0.10
    åŃIJéĩĮ
    -0.10
    ally
    -0.10
    ening
    -0.10
    ener
    -0.10
    ify
    -0.09
    quis
    -0.09
    ning
    -0.09
    ification
    -0.09
    ious
    -0.08
    POSITIVE LOGITS
    azzi
    0.09
    åĹŁ
    0.09
    åİ©
    0.09
    æĦ§
    0.09
    åķĸ
    0.09
    举æĸ¹è´¢å¯Į
    0.09
    arks
    0.09
    ·æĸ°
    0.09
    ży
    0.08
    ÑĢÑİ
    0.08
    Activations Density 0.010%

    No Known Activations