© 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. 61208
    Prev
    Next
    INDEX
    Explanations

    grazing on pasture

    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
    æī¼
    -0.10
    çªĿ
    -0.09
    å·¢
    -0.09
    ëĵł
    -0.09
    udu
    -0.09
    éľĨ
    -0.09
    amy
    -0.09
    artment
    -0.08
    mailer
    -0.08
    âĶģâĶģ
    -0.08
    POSITIVE LOGITS
    aus
    0.09
    åķĦ
    0.09
    å¨ĥ
    0.09
    ÙĦاÙĨ
    0.09
    Ñıд
    0.08
     Clem
    0.08
    æĦĶ
    0.08
    _mt
    0.08
    able
    0.08
    quir
    0.08
    Activations Density 0.015%

    No Known Activations