© 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. 32858
    Prev
    Next
    INDEX
    Explanations

    much/a lot comparative

    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
    åĭ¤å¥ĭ
    -0.10
    nesia
    -0.09
    æĥŃ
    -0.09
    è¿ĻéĩĮæĺ¯
    -0.08
    aghan
    -0.08
    èĩªè´Ł
    -0.08
    achen
    -0.08
     come
    -0.08
    åħ¹
    -0.08
    aring
    -0.08
    POSITIVE LOGITS
    æĬ½
    0.09
    ucked
    0.09
    BITS
    0.09
    çļ
    0.08
    rames
    0.08
    åļ¼
    0.08
     пÑĢиÑĩин
    0.08
    ä¸»å¼ł
    0.08
    ç»ıéªĮåĴĮ
    0.08
    throp
    0.08
    Activations Density 0.026%

    No Known Activations