© 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. 6715
    Prev
    Next
    INDEX
    Explanations

    team, education, training

    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
    ance
    -0.11
    ances
    -0.11
    undi
    -0.09
    èŤ
    -0.09
    ately
    -0.09
    bid
    -0.08
    æ¹į
    -0.08
    ãģĹãģ¾ãģĨ
    -0.08
    åīįæıIJæĺ¯
    -0.08
    arella
    -0.08
    POSITIVE LOGITS
    perature
    0.17
     ngũ
    0.11
    éĢĬ
    0.10
    atical
    0.09
    usc
    0.09
    -building
    0.09
     Hew
    0.09
    éĺŁéķ¿
    0.09
    UNC
    0.09
    spot
    0.09
    Activations Density 0.051%

    No Known Activations