© 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. 19952
    Prev
    Next
    INDEX
    Explanations

    team and teams

    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
     listing
    -0.08
    çĸı
    -0.08
    elic
    -0.08
    ä¸įåĪĨ
    -0.08
    verte
    -0.08
    åıĪä¸Ģ次
    -0.08
    åħ¥åı£
    -0.07
    寧
    -0.07
    åĩ¸
    -0.07
     vert
    -0.07
    POSITIVE LOGITS
    è¿ĻæĶ¯
    0.11
    èĬ±æł·
    0.10
    åIJĪä½ľä¼Ļä¼´
    0.10
    é¢ĵ
    0.09
    å®īç½®
    0.09
    åIJĪä½ľåħ³ç³»
    0.09
    éĵł
    0.09
    è¯ĥ
    0.09
    ä¸ĵ项èµĦéĩij
    0.09
    è£ħä¿®åħ¬åı¸
    0.09
    Activations Density 0.049%

    No Known Activations