© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 40030
    Prev
    Next
    INDEX
    Explanations

    Hewlett, Lewin, Lewd

    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
    adem
    -0.10
    æĤłæĤł
    -0.09
    late
    -0.09
    /off
    -0.09
    stellung
    -0.09
    ously
    -0.09
    ìķ¼
    -0.09
    tere
    -0.08
    uration
    -0.08
    oot
    -0.08
    POSITIVE LOGITS
    minster
    0.10
    åĽŀäºĭ
    0.10
    riting
    0.10
    ening
    0.09
    ะ
    0.09
    åı¯æĥľ
    0.09
    illac
    0.09
    ãģªãĤĭ
    0.09
    ãģŀ
    0.09
    lobe
    0.09
    Activations Density 0.016%

    No Known Activations