© 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. 19274
    Prev
    Next
    INDEX
    Explanations

    units of time and measurement

    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
    åºŁ
    -0.09
    ijo
    -0.09
    born
    -0.08
    éĻĦå±ŀ
    -0.08
    çīĩ
    -0.08
     dime
    -0.07
     bulk
    -0.07
    _MEDIUM
    -0.07
     кл
    -0.07
     اÙĦÙħست
    -0.07
    POSITIVE LOGITS
    è°ģèĥ½
    0.09
    弧
    0.09
     Ñĩего
    0.09
    alon
    0.09
    è¸ŀ
    0.09
    /lg
    0.09
     Gast
    0.08
    è´»
    0.08
    é±
    0.08
    è¾ĺ
    0.08
    Activations Density 0.039%

    No Known Activations