© 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. 2219
    Prev
    Next
    INDEX
    Explanations

    having followed by a phrase

    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
    ALAR
    -0.09
    ãĥ³
    -0.09
    asel
    -0.08
    é¦ĸåıij
    -0.08
    çľ¯
    -0.08
    /qt
    -0.08
    æĿµ
    -0.08
    ä¸į该
    -0.08
    ogens
    -0.08
    phere
    -0.07
    POSITIVE LOGITS
    æĪijä»¬ä¹Ł
    0.11
    èĤ¥
    0.11
    atched
    0.09
    å¤ļå¹´çļĦ
    0.09
    æĪij们éĥ½
    0.09
    icho
    0.09
    оÑī
    0.08
    aldi
    0.08
    æĪijä¹Ł
    0.08
    é«ĺéĢŁ
    0.08
    Activations Density 0.009%

    No Known Activations