© 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. 57543
    Prev
    Next
    INDEX
    Explanations

    name, space, care, graduated, woke

    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
    ynn
    -0.09
    à¤Ľ
    -0.09
    à¸ĵ
    -0.08
    leans
    -0.08
    lein
    -0.08
     Crack
    -0.07
    é¢ī
    -0.07
     Wich
    -0.07
    ecurity
    -0.07
    Ñģел
    -0.07
    POSITIVE LOGITS
    bare
    0.09
    åľ¨è¿ĩ渡
    0.09
    anco
    0.09
    Ī
    0.09
    æµģæ°´
    0.09
    æĢł
    0.08
    é«ĺå°Ķ夫
    0.08
    ading
    0.08
    ä¸ĢæĿ¡é¾Ļ
    0.08
    è
    0.08
    Activations Density 0.530%

    No Known Activations