© 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. 18328
    Prev
    Next
    INDEX
    Explanations

    seamless [access, integration, support, transition]

    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
    avery
    -0.09
    aceous
    -0.09
    纳æĸ¯
    -0.08
    Ñģкое
    -0.08
    acer
    -0.08
    iever
    -0.08
    æ¨Ĺ
    -0.08
    ủng
    -0.08
     uneven
    -0.08
    Slash
    -0.08
    POSITIVE LOGITS
    éļĻ
    0.14
    ingly
    0.11
    æ°ijå¿ĥ
    0.10
    รà¸Ńย
    0.10
     repro
    0.10
    æݥ轨
    0.10
    å°ıäºĭ
    0.10
    åľ°å¸¦
    0.09
     curt
    0.09
    æĹłç¼Ŀ
    0.09
    Activations Density 0.004%

    No Known Activations