© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20485
    Prev
    Next
    INDEX
    Explanations

    jo-ann, ann, jo ann, joanne

    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
    اÙĥ
    -0.10
    æªĶ
    -0.09
    rary
    -0.09
    owing
    -0.09
    urrent
    -0.09
    REM
    -0.09
    åł¡
    -0.09
    纤
    -0.09
    åĬŃ
    -0.08
    ftime
    -0.08
    POSITIVE LOGITS
    sWith
    0.10
    auce
    0.10
     коллекÑĤив
    0.10
    opoulos
    0.10
    aly
    0.10
    als
    0.09
    éºŁ
    0.09
    гла
    0.08
    Ñīий
    0.08
    ments
    0.08
    Activations Density 0.157%

    No Known Activations