© 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. 22917
    Prev
    Next
    INDEX
    Explanations

    principles of

    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
    ICC
    -0.10
    ingly
    -0.10
    pedia
    -0.10
    ÑĢажа
    -0.10
    åĽŀé¦ĸ
    -0.09
    ness
    -0.09
    enic
    -0.09
    liers
    -0.09
    aint
    -0.09
    uber
    -0.08
    POSITIVE LOGITS
    æĢ§çļĦ
    0.11
    åİŁåīĩ
    0.10
    bred
    0.10
    AAC
    0.10
    èĤĦ
    0.09
    iller
    0.09
    -agent
    0.09
    ä¸įåĬ¨
    0.09
    vent
    0.09
    .stdin
    0.09
    Activations Density 0.025%

    No Known Activations