© 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. 11163
    Prev
    Next
    INDEX
    Explanations

    need to know

    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
     synced
    -0.09
    _GP
    -0.08
    èĮ«èĮ«
    -0.08
    ç¿»
    -0.08
    ãģĹãģ£
    -0.08
    è³¢
    -0.08
     perv
    -0.08
    æ¯ıä¸Ģ天
    -0.07
    èĩ´çĶµ
    -0.07
     motorcycles
    -0.07
    POSITIVE LOGITS
    _needed
    0.14
     needed
    0.13
     necessary
    0.13
    Needed
    0.12
    çļĦä¸ĢåĪĩ
    0.12
    å¿ħè¦ģ
    0.12
    å¿ħè¦ģçļĦ
    0.12
    æīĢéľĢçļĦ
    0.11
     необÑħодим
    0.11
    needed
    0.11
    Activations Density 0.210%

    No Known Activations