© 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. 49481
    Prev
    Next
    INDEX
    Explanations

    linux kernel drivers and modes

    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
     пÑĢоизвод
    -0.09
    容è²Į
    -0.09
    ickle
    -0.09
    andard
    -0.09
    åĩ¤
    -0.09
    Sci
    -0.09
     mid
    -0.08
    endum
    -0.08
    aña
    -0.08
    ture
    -0.08
    POSITIVE LOGITS
    æ±ģ
    0.10
    #line
    0.10
    led
    0.09
    pta
    0.09
    å®ŀäºĭ
    0.08
    ooter
    0.08
    ApiClient
    0.08
    ä¾Ķ
    0.08
    åºĦ
    0.08
    _ctxt
    0.08
    Activations Density 0.025%

    No Known Activations