© 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. 49214
    Prev
    Next
    INDEX
    Explanations

    smiles, smoking, smells, smoky, smiling

    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
    ModelAttribute
    -0.10
    umph
    -0.09
    igram
    -0.09
    à¹ģสà¸ĩ
    -0.09
    lide
    -0.09
    شت
    -0.09
    иÑĤеÑģÑĮ
    -0.09
    orate
    -0.08
    terior
    -0.08
    eer
    -0.08
    POSITIVE LOGITS
    ooth
    0.11
    PING
    0.10
    /sm
    0.10
    ån
    0.09
    wich
    0.09
    allest
    0.09
    iesz
    0.09
    éļ¼
    0.09
    creen
    0.09
    æ±ĩ
    0.09
    Activations Density 0.043%

    No Known Activations