© 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. 52960
    Prev
    Next
    INDEX
    Explanations

    young pets

    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
     meisten
    -0.08
    InBackground
    -0.08
    æijĦ
    -0.08
    ObjectOfType
    -0.08
    并ä¸į代表
    -0.08
    offs
    -0.08
    éĽģ
    -0.08
    aways
    -0.08
    azen
    -0.08
    .Uint
    -0.08
    POSITIVE LOGITS
    hood
    0.11
    lü
    0.11
    ãģĦãĤĭ
    0.10
    izer
    0.10
    itas
    0.10
    iali
    0.10
    è·Ľ
    0.09
    iate
    0.09
    kind
    0.08
    е
    0.08
    Activations Density 0.004%

    No Known Activations