© 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. 23572
    Prev
    Next
    INDEX
    Explanations

    video file extensions

    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
    adal
    -0.08
     Cors
    -0.08
    quo
    -0.08
    èĽ©
    -0.08
    uess
    -0.08
    etal
    -0.08
    使åij½æĦŁ
    -0.08
    çĤ¯
    -0.08
    åµĺ
    -0.08
    ç©·
    -0.07
    POSITIVE LOGITS
    好çľĭçļĦ
    0.10
    ucher
    0.09
    icit
    0.09
    æĬĬä½ł
    0.08
    é¹ľ
    0.08
    åŀŃ
    0.08
    Dirty
    0.08
    åıĭ好
    0.08
     Jou
    0.08
    OLER
    0.08
    Activations Density 0.002%

    No Known Activations