© 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. 23001
    Prev
    Next
    INDEX
    Explanations

    slack, idle, Acks

    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
    èħ±
    -0.11
    иÑģк
    -0.10
    æīĢ以说
    -0.09
    ãĤĤãģ£ãģ¨
    -0.09
    ello
    -0.09
    å¿«
    -0.09
     Terrace
    -0.09
    仪
    -0.09
    geist
    -0.09
    ksen
    -0.08
    POSITIVE LOGITS
    NOWLED
    0.11
    riv
    0.10
    buster
    0.10
    rok
    0.09
    ÙĪØ®
    0.09
    ening
    0.08
    ×ķת
    0.08
    ç¾¤å²Ľ
    0.08
    uate
    0.08
    sters
    0.08
    Activations Density 0.007%

    No Known Activations