© 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. 39300
    Prev
    Next
    INDEX
    Explanations

    wrapping and bags

    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
    REM
    -0.11
    acus
    -0.09
    åĵģ
    -0.09
    mina
    -0.09
    路边
    -0.09
    åĢĻ
    -0.09
     ÐĺнÑĤеÑĢнеÑĤ
    -0.09
     foam
    -0.09
    shot
    -0.09
     ÐijолÑĮ
    -0.09
    POSITIVE LOGITS
     Millennium
    0.09
    产ä¸ļåıijå±ķ
    0.09
    -covered
    0.08
    èŁł
    0.08
    çĹ´
    0.08
    Tür
    0.08
    ä¸Ńåľº
    0.08
    åīIJ
    0.08
    ija
    0.08
    ï¸ı
    0.07
    Activations Density 0.014%

    No Known Activations