© 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. 38607
    Prev
    Next
    INDEX
    Explanations

    have a/an/done/no/used/created

    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
    bib
    -0.09
    å¼¹
    -0.09
    ../../../../
    -0.09
    (cn
    -0.08
    dn
    -0.08
    wing
    -0.08
    请大家
    -0.08
     söz
    -0.08
    å§ij
    -0.08
    å¹²èĦĨ
    -0.08
    POSITIVE LOGITS
    éĹ²ç½®
    0.13
    éĵ²
    0.10
    .bs
    0.10
    æ¶Īè´¹éľĢæ±Ĥ
    0.10
    éĸĴ
    0.10
     Jacqueline
    0.09
    çİ°æľī
    0.09
    æ´»
    0.09
    对ç«ĭ
    0.09
    .conf
    0.09
    Activations Density 0.127%

    No Known Activations