© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53350
    Prev
    Next
    INDEX
    Explanations

    capture

    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
    å±ķæľĽ
    -0.11
    æīİ
    -0.10
    å²ij
    -0.09
    åŁºæķ°
    -0.08
    .asc
    -0.08
    ogie
    -0.08
     cellspacing
    -0.08
     Commissioners
    -0.08
     zx
    -0.08
    ä¸Ģçķª
    -0.08
    POSITIVE LOGITS
    æįķæįī
    0.11
    çķĻä½ı
    0.11
    ä½ıäºĨ
    0.10
     capturing
    0.10
     captures
    0.10
     capture
    0.10
    ç»Ĩèħ»
    0.10
    åĨįçİ°
    0.10
    _capture
    0.10
    capture
    0.10
    Activations Density 0.080%

    No Known Activations