© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22004
    Prev
    Next
    INDEX
    Explanations

    human resources department

    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
    ry
    -0.10
    ãģĵãģ¨
    -0.10
    ICATION
    -0.09
    ä½Ĩä¸įéĻIJäºİ
    -0.09
    ofs
    -0.09
    ê¸ī
    -0.09
    ryo
    -0.08
    uy
    -0.08
    rolls
    -0.08
    edReader
    -0.08
    POSITIVE LOGITS
    fully
    0.10
    aceous
    0.10
    ----------------------------------------------------------------
    0.09
    lox
    0.09
    istory
    0.09
    le
    0.08
    رÙĥ
    0.08
    åĨįè§ģ
    0.08
    对ä»ĺ
    0.08
    uset
    0.08
    Activations Density 0.169%

    No Known Activations