© 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. 54582
    Prev
    Next
    INDEX
    Explanations

    days ago or after

    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
    emas
    -0.10
    irim
    -0.10
    å½ĵå¹´
    -0.10
    æŶåĪ»
    -0.10
    orio
    -0.10
    åĪ°æŶåĢĻ
    -0.09
    ä¸ĭä¸Ģ代
    -0.09
    ãĥIJãĥ³ãĥī
    -0.09
    éģĩéļ¾
    -0.09
    年代
    -0.09
    POSITIVE LOGITS
    OfWeek
    0.19
     ÑĢождениÑı
    0.17
    dream
    0.13
    quil
    0.12
    iating
    0.11
    åŃIJéĩĮ
    0.11
    åĴĮåľ°åĮº
    0.11
    brid
    0.10
    ì§ľ
    0.10
    break
    0.10
    Activations Density 0.142%

    No Known Activations