© 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. 33653
    Prev
    Next
    INDEX
    Explanations

    ASP.NET

    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
    vo
    -0.09
    anguages
    -0.08
    裤
    -0.08
    è¾ķ
    -0.08
    zelf
    -0.08
    posable
    -0.08
    IVES
    -0.08
    phas
    -0.08
    hift
    -0.08
    Robin
    -0.08
    POSITIVE LOGITS
    ellant
    0.10
    olini
    0.09
    èĻij
    0.09
    ТÐĺ
    0.09
    eed
    0.09
    à¸ģระà¸Ĺ
    0.09
    abilities
    0.09
    æ¬Ĭ
    0.09
    itals
    0.09
    oon
    0.09
    Activations Density 0.062%

    No Known Activations