© 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. 56958
    Prev
    Next
    INDEX
    Explanations

    family and associated contexts

    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
    marsh
    -0.10
    achu
    -0.09
    iami
    -0.09
    ÑģÑĤо
    -0.09
     dul
    -0.08
    åĪĴåĪĨ
    -0.08
    主宰
    -0.08
    shaw
    -0.08
    zo
    -0.08
    è¡¡
    -0.08
    POSITIVE LOGITS
     alike
    0.09
    /ion
    0.08
    åŃĶéĽĢ
    0.08
    _FEED
    0.08
     ayrı
    0.08
    urre
    0.08
    æłī
    0.08
    éĺī
    0.08
    严谨
    0.08
     Gram
    0.08
    Activations Density 0.011%

    No Known Activations