© 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. 55489
    Prev
    Next
    INDEX
    Explanations

    tv channels and volume

    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
    ä»İä¸ļ
    -0.09
    bao
    -0.09
    ä½İä»·
    -0.09
     ÑĢаÑģпÑĢоÑģÑĤ
    -0.08
    æµģ产
    -0.08
    å¹²èѦ
    -0.08
    亲åıĭ
    -0.08
    å®ŀçī©
    -0.08
     anomal
    -0.08
    ä»ĵ
    -0.08
    POSITIVE LOGITS
    æ¡£
    0.10
    æį»
    0.09
    è°Ļ
    0.09
    æªĶ
    0.09
    draft
    0.09
    çĶµè§Ĩæľº
    0.09
     Spears
    0.08
    habi
    0.08
    htag
    0.08
    DOWN
    0.08
    Activations Density 0.088%

    No Known Activations