© 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. 30758
    Prev
    Next
    INDEX
    Explanations

    Robinson or Webster

    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
    åĶ§
    -0.10
    imuth
    -0.10
    igne
    -0.10
    ÑĤоÑĢ
    -0.10
    ño
    -0.10
    ision
    -0.09
    ioned
    -0.09
     Abbey
    -0.09
    人æ°ijæľįåĬ¡
    -0.09
    大åıĶ
    -0.09
    POSITIVE LOGITS
    andi
    0.10
    «
    0.10
    -minded
    0.10
    ì±ħ
    0.10
     minded
    0.10
    azzi
    0.09
    ekt
    0.09
    anda
    0.09
    hood
    0.09
    èĩ
    0.09
    Activations Density 0.003%

    No Known Activations