© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38179
    Prev
    Next
    INDEX
    Explanations

    a bit of

    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
    ãĤĤãģ£ãģ¨
    -0.08
    Lite
    -0.08
    ed
    -0.08
    è°ģ
    -0.08
    æ£Ĥ
    -0.08
    许å¤ļ人
    -0.08
    \$
    -0.08
    æĥ³åĪ°
    -0.07
     cheapest
    -0.07
    ä¸įå°ij人
    -0.07
    POSITIVE LOGITS
    ìĶ©
    0.13
    ÑĩиÑģлен
    0.10
    ãģĵãģ¨ãģ§ãģĻ
    0.10
    媵
    0.09
    家è£ħ
    0.09
    onomy
    0.09
    ỡ
    0.09
    ariat
    0.09
    _Property
    0.09
    æŶåĢĻ
    0.09
    Activations Density 0.009%

    No Known Activations