© 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. 52299
    Prev
    Next
    INDEX
    Explanations

    Nolan, Brennan names

    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
    é»ĺå¥ij
    -0.11
    çī§
    -0.10
    esion
    -0.09
    å¿ĥä¸ŃçļĦ
    -0.09
    ariat
    -0.09
    пол
    -0.09
    ç¦ıç¥ī
    -0.09
    殳
    -0.09
    rike
    -0.09
    inue
    -0.09
    POSITIVE LOGITS
    ../
    0.10
    cy
    0.09
    chron
    0.09
    urally
    0.09
    yst
    0.09
    tics
    0.09
    usk
    0.08
    è´§æŀ¶
    0.08
    IRO
    0.08
    uxtap
    0.08
    Activations Density 0.004%

    No Known Activations