© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 32321
    Prev
    Next
    INDEX
    Explanations

    strong

    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
    ä¸ĩåįĥ
    -0.10
    noc
    -0.10
    ç§įç§į
    -0.09
    alon
    -0.09
    çͬ
    -0.08
    à¹Īาà¸Ļ
    -0.08
    详ç»Ĩä»ĭç»į
    -0.08
     foregoing
    -0.08
    rough
    -0.08
    ä¸īåĪĨä¹ĭä¸Ģ
    -0.08
    POSITIVE LOGITS
     mẽ
    0.20
    holds
    0.14
    haft
    0.13
    erness
    0.12
    est
    0.12
    iveness
    0.11
    /fast
    0.09
    ivas
    0.09
     emphasis
    0.09
    -hearted
    0.09
    Activations Density 0.091%

    No Known Activations