© 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. 58188
    Prev
    Next
    INDEX
    Explanations

    affirmative statements or conditions

    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
     Toilet
    -0.09
    èĽ®
    -0.08
     Hut
    -0.08
    æľªæĪIJå¹´
    -0.08
    æ¯Ľ
    -0.08
    åİķ
    -0.08
    éĻ·åħ¥äºĨ
    -0.08
     narz
    -0.08
    çŀĭ
    -0.08
    à¸Ńà¸ĩ
    -0.08
    POSITIVE LOGITS
    çĨ¨
    0.09
    razier
    0.09
     же
    0.09
    INVAL
    0.09
    çļĦåľ°æĸ¹
    0.09
    æĿı
    0.08
    .Designer
    0.08
    imuth
    0.08
    管家
    0.08
    .assertThat
    0.08
    Activations Density 0.099%

    No Known Activations