© 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. 62888
    Prev
    Next
    INDEX
    Explanations

    app store

    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
    zion
    -0.11
    _PRIORITY
    -0.09
    æĻºéĢł
    -0.09
    èĵį
    -0.09
    袪
    -0.09
    hana
    -0.09
    _COLL
    -0.09
    å°Ĭ
    -0.09
    æīĪ
    -0.09
     недо
    -0.09
    POSITIVE LOGITS
    åķĨåºĹ
    0.09
     cracked
    0.09
    bate
    0.08
    åħħ
    0.08
    éĻ¢
    0.08
    tern
    0.08
    å¸Ĥåľºç«ŀäºī
    0.08
    èĨij
    0.08
    纵横
    0.08
    åĪĩ
    0.08
    Activations Density 0.151%

    No Known Activations