© 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. 2471
    Prev
    Next
    INDEX
    Explanations

    Columbia University or Center

    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
    CADE
    -0.11
    们
    -0.10
    ORED
    -0.10
    engers
    -0.09
    tings
    -0.09
    ãģĭãģĦ
    -0.09
    bled
    -0.09
    ness
    -0.09
    emens
    -0.08
    uture
    -0.08
    POSITIVE LOGITS
    sic
    0.10
    æĪijè¿ĺ
    0.09
    vÃŃ
    0.09
    ripper
    0.09
    arity
    0.09
    inate
    0.08
    åĢº
    0.08
    arding
    0.08
    èľ»
    0.08
    çĿļ
    0.08
    Activations Density 0.019%

    No Known Activations