© 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. 2115
    Prev
    Next
    INDEX
    Explanations

    noticed that

    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
    à¹Į
    -0.12
    ictory
    -0.10
    /ph
    -0.09
    GI
    -0.09
    æĪijçŁ¥éģĵ
    -0.09
    iant
    -0.09
    FLT
    -0.09
    è¦ģéĹ»
    -0.09
    çĮĹ
    -0.09
    çĶļ
    -0.09
    POSITIVE LOGITS
    ably
    0.16
    éĻIJãĤĬ
    0.11
    iced
    0.11
    egov
    0.10
    _raise
    0.09
    åĭĥåĭĥ
    0.09
    amac
    0.09
    å¯Ł
    0.09
     keen
    0.09
    æľī人
    0.09
    Activations Density 0.028%

    No Known Activations