© 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. 56292
    Prev
    Next
    INDEX
    Explanations

    Cousins, Green, Lovato, Boss, Airtel

    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
    å¢ħ
    -0.09
    acl
    -0.09
    èı½
    -0.09
    ulet
    -0.09
    åī²
    -0.08
    åĪĨæĶ¯
    -0.08
    åIJĪæĪIJ
    -0.08
     scaleY
    -0.08
    æŀ¥
    -0.08
    èµ·èįī
    -0.08
    POSITIVE LOGITS
    çĥŃ带
    0.10
    odal
    0.09
    èīĩ
    0.09
    èĢģåħ¬
    0.09
     ÙĨÙģسÙĩا
    0.09
    yped
    0.09
    楼主
    0.09
    .listen
    0.09
    egin
    0.08
    TINGS
    0.08
    Activations Density 0.021%

    No Known Activations