© 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. 58245
    Prev
    Next
    INDEX
    Explanations

    making up or performing actions

    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
    imately
    -0.10
    ä¸ľæµ·
    -0.10
    -makers
    -0.10
    InputBorder
    -0.09
    IONS
    -0.09
    ãģĤãĤĮ
    -0.09
     ÑģкаÑĩ
    -0.09
    egot
    -0.09
    æ°¾
    -0.09
    opus
    -0.09
    POSITIVE LOGITS
    ings
    0.13
    able
    0.11
    ing
    0.10
    -
    0.09
    ingly
    0.09
    nl
    0.09
    ng
    0.09
    st
    0.09
    er
    0.09
    overs
    0.08
    Activations Density 0.117%

    No Known Activations