© 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. 9818
    Prev
    Next
    INDEX
    Explanations

    website domain 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
    çIJļ
    -0.08
     lav
    -0.08
     Lav
    -0.08
    缴æĴŃ
    -0.08
    æµģä¼ł
    -0.08
    ä»Ļ
    -0.08
    åĶ±
    -0.08
    6
    -0.08
    lav
    -0.07
    çłĶ
    -0.07
    POSITIVE LOGITS
    追究
    0.11
    å°ıå¿ĥ
    0.11
     muff
    0.10
    lify
    0.10
    ICODE
    0.10
    elps
    0.10
    .gnu
    0.09
    åį°è±¡
    0.09
    /repos
    0.09
    _FMT
    0.09
    Activations Density 0.053%

    No Known Activations