© 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. 2584
    Prev
    Next
    INDEX
    Explanations

    side effects

    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
    æĿµ
    -0.10
    çŀ½
    -0.10
    -ever
    -0.10
    èŁĭ
    -0.09
    å¾Ģå¤ĸ
    -0.09
    éĢĭ
    -0.09
    çī¹çĤ¹æĺ¯
    -0.09
    ESTAMP
    -0.09
    owie
    -0.09
    罩
    -0.08
    POSITIVE LOGITS
     bomb
    0.08
    头æĿ¡
    0.08
    .transitions
    0.08
    LabelText
    0.08
    _quotes
    0.08
    ãģĹãģ¾
    0.08
    _None
    0.08
    ÑĢÑı
    0.08
    ç¬ĶèĢħ
    0.08
    QualifiedName
    0.08
    Activations Density 0.005%

    No Known Activations