© 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. 39303
    Prev
    Next
    INDEX
    Explanations

    share, shared, sharing

    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
     ahead
    -0.10
    Ahead
    -0.10
     Ahead
    -0.09
    é¢ĨåħĪ
    -0.09
    UIS
    -0.08
    سبÙĤ
    -0.08
    åīįéĿ¢
    -0.08
    endon
    -0.08
     Gala
    -0.08
    ahead
    -0.08
    POSITIVE LOGITS
     sentiment
    0.10
    裱
    0.09
    éĻĦ
    0.09
    ä»»ä½ķ人
    0.09
    FromString
    0.09
    åħ±åIJĮä½ĵ
    0.09
    ä¸įå®Į
    0.09
    sez
    0.08
    åij»
    0.08
    AEA
    0.08
    Activations Density 0.021%

    No Known Activations