© 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. 34671
    Prev
    Next
    INDEX
    Explanations

    Gap Year, Cup, Push, missionary

    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
    è£
    -0.10
    åħ·ä½ĵåĨħ容
    -0.09
    째
    -0.09
     rescue
    -0.08
    æ·Ļ
    -0.08
     вз
    -0.08
    åŁİå¸Ĥ群
    -0.08
    æijĺç¼ĸ
    -0.08
    çĸµ
    -0.08
    _skip
    -0.08
    POSITIVE LOGITS
    éĢĢ
    0.11
    edom
    0.10
     Moss
    0.10
    使åij½
    0.09
    é©´
    0.09
    代åĬŀ
    0.09
    åı¸
    0.09
    åĽłåľ°åĪ¶å®ľ
    0.09
    è®·
    0.09
    è¡£çī©
    0.09
    Activations Density 0.009%

    No Known Activations