© 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. 34036
    Prev
    Next
    INDEX
    Explanations

    sequences of letters or character counts

    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
    馨
    -0.11
    çĨ¨
    -0.10
    chia
    -0.09
    -addon
    -0.09
    èħ»
    -0.09
    讵
    -0.09
    éĦĻ
    -0.09
    ä¸įå¿ĺ
    -0.08
    éĢ
    -0.08
    irsch
    -0.08
    POSITIVE LOGITS
    æĹĹå¸ľ
    0.12
    omi
    0.09
     Hick
    0.09
    /rest
    0.08
    æŀľæ±ģ
    0.08
    oldem
    0.08
    OKIE
    0.08
    xon
    0.08
    zzle
    0.08
    fer
    0.08
    Activations Density 0.006%

    No Known Activations