© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37021
    Prev
    Next
    INDEX
    Explanations

    alban or albaretto

    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
    alloc
    -0.10
    èĬľ
    -0.10
    ophile
    -0.09
    ager
    -0.09
    unist
    -0.09
    icular
    -0.09
    bull
    -0.08
    icip
    -0.08
    ducible
    -0.08
    elves
    -0.08
    POSITIVE LOGITS
    GORITH
    0.09
    ä¸Ģ代
    0.08
    avit
    0.08
    onn
    0.08
    èĶij
    0.08
    onso
    0.08
    تÙĪ
    0.08
    æ§Ľ
    0.08
    ãģ¾ãģ¾
    0.08
    纪å§ĶçĽijå§Ķ
    0.08
    Activations Density 0.034%

    No Known Activations