© 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. 58801
    Prev
    Next
    INDEX
    Explanations

    able to understand

    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
    该éĻ¢
    -0.11
    isia
    -0.09
    Ñģли
    -0.08
    亲åĪĩ
    -0.08
    ACHI
    -0.08
    ivy
    -0.08
    榫
    -0.08
    对æĸ¹
    -0.08
    _UNICODE
    -0.08
    aber
    -0.08
    POSITIVE LOGITS
    æĪij们
    0.24
    æĪij们就
    0.21
    æĪijåĢij
    0.20
    æĪij们åı¯ä»¥
    0.20
    æĪijä»¬åľ¨
    0.20
    让æĪij们
    0.20
    æĪij们å¿ħé¡»
    0.19
    æĪij们éĥ½
    0.19
    æĪijä»¬ä¹Ł
    0.19
    æĪij们åºĶ该
    0.19
    Activations Density 0.190%

    No Known Activations