© 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. 38096
    Prev
    Next
    INDEX
    Explanations

    parma, worcestershire, ermigiano

    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
    zin
    -0.09
    -minded
    -0.09
    ntax
    -0.09
    å«Į
    -0.08
    ouce
    -0.08
    èĪ«
    -0.08
    ä¸Ģ对
    -0.08
    Ñħодим
    -0.08
     ÙĪØ®
    -0.08
    (problem
    -0.08
    POSITIVE LOGITS
    èĪįä¸įå¾Ĺ
    0.09
    itecture
    0.09
    standing
    0.09
    è£Ķ
    0.09
    å¼ĢéĺĶ
    0.08
    al
    0.08
    sa
    0.08
    eter
    0.08
    åħ¬åĬ¡
    0.08
    san
    0.08
    Activations Density 0.002%

    No Known Activations