© 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. 55666
    Prev
    Next
    INDEX
    Explanations

    sh words followed by specific endings

    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
    ally
    -0.10
    lectic
    -0.10
    mente
    -0.09
    uche
    -0.09
    chio
    -0.09
    usz
    -0.09
    é¦ĸå¸Ń
    -0.09
    andbox
    -0.09
    gen
    -0.09
    ucci
    -0.09
    POSITIVE LOGITS
    èŁĨ
    0.12
    èĢģ人家
    0.12
    akespeare
    0.12
    PING
    0.12
    ãģ£ãģ¨
    0.12
    (sh
    0.12
    peare
    0.11
    ields
    0.11
    apiro
    0.11
    ooting
    0.11
    Activations Density 0.178%

    No Known Activations