© 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. 7059
    Prev
    Next
    INDEX
    Explanations

    Mr titles and names

    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
    ÑĢÑĥÑģ
    -0.10
    ÙĦاÙħ
    -0.10
    ÑģÑĤÑĢ
    -0.09
    egis
    -0.09
    erman
    -0.09
    à¸Ķาว
    -0.09
    inkel
    -0.09
    bred
    -0.09
    rite
    -0.09
    phony
    -0.09
    POSITIVE LOGITS
    们çļĦ
    0.11
    ships
    0.11
    åĢij
    0.11
    åľ°æ¯¯
    0.10
    orage
    0.09
    acci
    0.09
    è¯ŀ
    0.09
    éĻĽä¸ĭ
    0.09
    aining
    0.09
    çĪ·
    0.09
    Activations Density 0.027%

    No Known Activations