© 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. 55482
    Prev
    Next
    INDEX
    Explanations

    act like

    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
    æĪijå¿ĥéĩĮ
    -0.10
    管çIJĨå±Ĥ
    -0.10
    ç¾İæľ¯é¦Ĩ
    -0.09
    ç¢İ
    -0.08
    çī¯
    -0.08
    ä¸Ģä½ĵ
    -0.08
    åı«åģļ
    -0.08
     Thorn
    -0.08
    表æī¬
    -0.08
    éĢļæĬ¥
    -0.08
    POSITIVE LOGITS
    åĥı个
    0.09
    éĤ¸
    0.09
    ä¸Ģåī¯
    0.09
    çĶ©
    0.09
    PIX
    0.09
    ¡°
    0.09
     какие
    0.08
    imax
    0.08
    uate
    0.08
    imers
    0.08
    Activations Density 0.010%

    No Known Activations