© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20177
    Prev
    Next
    INDEX
    Explanations

    any later

    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
    ends
    -0.10
     вÑģего
    -0.09
    /renderer
    -0.09
    åħ¨ä½ĵ
    -0.09
    stor
    -0.09
    ymmetric
    -0.09
    æĪIJç«ĭ以æĿ¥
    -0.08
    avings
    -0.08
    emm
    -0.08
    ened
    -0.08
    POSITIVE LOGITS
    THING
    0.20
    /all
    0.19
    æĻĤåĢĻ
    0.16
    place
    0.15
    thin
    0.14
    ones
    0.12
    ways
    0.12
    ons
    0.12
    body
    0.11
    things
    0.11
    Activations Density 0.086%

    No Known Activations