© 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. 4063
    Prev
    Next
    INDEX
    Explanations

    without restriction

    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
    ãģĹãģ
    -0.10
    å¥ł
    -0.10
    é«ij
    -0.09
    为é¦ĸ
    -0.09
    IMIT
    -0.09
    çŁ¥éģĵäºĨ
    -0.08
    foil
    -0.08
    panion
    -0.08
    åIJĬ
    -0.08
    åĨ¥
    -0.08
    POSITIVE LOGITS
    åľ°
    0.10
    lessly
    0.10
     Leone
    0.09
    è¿Ļ群
    0.09
    stro
    0.08
    iless
    0.08
    bull
    0.08
    ä»»ä½ķ人
    0.08
    ably
    0.08
    åĵªæĢķæĺ¯
    0.08
    Activations Density 0.115%

    No Known Activations