© 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. 6558
    Prev
    Next
    INDEX
    Explanations

    percentages and units

    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
    SupportedContent
    -0.12
    иÑģк
    -0.10
    ãĤį
    -0.10
    _FUNCTION
    -0.10
    严ç¦ģ
    -0.10
    ableView
    -0.10
    ä½¼
    -0.10
    RIES
    -0.09
    éļĻ
    -0.09
    Insensitive
    -0.09
    POSITIVE LOGITS
    0
    0.08
    -plus
    0.08
    artment
    0.08
     trừ
    0.07
     ef
    0.07
    acre
    0.07
    æIJģ
    0.07
    ener
    0.07
    -en
    0.07
    jac
    0.07
    Activations Density 0.167%

    No Known Activations