© 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. 26786
    Prev
    Next
    INDEX
    Explanations

    magazines

    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
    æѧ
    -0.10
    ç¼Ĩ
    -0.10
    erk
    -0.09
    ãĤ£
    -0.09
    CAPE
    -0.09
    outh
    -0.09
     Lug
    -0.09
    à¹Į
    -0.08
    ened
    -0.08
    /no
    -0.08
    POSITIVE LOGITS
    åĩıèĤ¥
    0.09
    uide
    0.09
    ellaneous
    0.09
    à¹ģà¸Ĥ
    0.09
    -worthy
    0.08
    ö
    0.08
    andatory
    0.08
    ARCH
    0.08
    WSC
    0.08
    enty
    0.08
    Activations Density 0.016%

    No Known Activations