© 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. 31550
    Prev
    Next
    INDEX
    Explanations

    not followed by verb or adjective

    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
    otime
    -0.09
    roc
    -0.08
     Cobb
    -0.08
    rotch
    -0.08
    ç»ĥä¹ł
    -0.08
    åįĥå¹´
    -0.08
    ifu
    -0.08
     ÑĤоже
    -0.07
    ech
    -0.07
    æħĪåĸĦ
    -0.07
    POSITIVE LOGITS
    åī¯å±Ģéķ¿
    0.11
    èĨĤ
    0.10
    è¦ģæĬĬ
    0.10
    ynn
    0.09
    atron
    0.09
    å³»
    0.09
    _NATIVE
    0.09
    èµ°åľ¨
    0.09
    建çŃijä¸ļ
    0.09
    éĵ§
    0.09
    Activations Density 0.069%

    No Known Activations