© 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. 32043
    Prev
    Next
    INDEX
    Explanations

    all together or all in

    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
    esk
    -0.08
    ester
    -0.08
    part
    -0.07
    esco
    -0.07
     KY
    -0.07
    æĸ¯é¡¿
    -0.07
    hir
    -0.07
     eb
    -0.07
    esting
    -0.07
    dom
    -0.07
    POSITIVE LOGITS
    综åIJĪåĪ©çĶ¨
    0.10
    ä¾ł
    0.10
    绿水
    0.10
    è´²
    0.10
    媳å¦ĩ
    0.09
    ëį°
    0.09
    erset
    0.09
    ynos
    0.09
    _atts
    0.09
    åĴĮæľįåĬ¡
    0.09
    Activations Density 0.008%

    No Known Activations