© 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. 63200
    Prev
    Next
    INDEX
    Explanations

    taking over roles or positions

    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
    atu
    -0.09
    天èĬ±æĿ¿
    -0.08
    æµ·æ°´
    -0.08
    ambi
    -0.08
    è§Ħ磩
    -0.08
    doctrine
    -0.08
    èıŁ
    -0.08
    reb
    -0.08
    _vi
    -0.08
    _NUMERIC
    -0.08
    POSITIVE LOGITS
    åı®
    0.09
    åİŁæľīçļĦ
    0.09
    åºĩ
    0.09
    éĩįä»»
    0.09
    主ä½ĵ责任
    0.09
    沸èħ¾
    0.09
     вмеÑģÑĤ
    0.09
    eload
    0.09
    è¿Ľè¡Įåħ¨éĿ¢
    0.08
    代
    0.08
    Activations Density 0.043%

    No Known Activations