© 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. 1398
    Prev
    Next
    INDEX
    Explanations

    product attributes and types

    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
    ìĤ¬íķŃ
    -0.10
    ajan
    -0.10
    æ¶İ
    -0.10
    Ī
    -0.10
    ÑĢ
    -0.09
     дело
    -0.09
    ANCE
    -0.09
    CriticalSection
    -0.09
    orta
    -0.09
    /she
    -0.09
    POSITIVE LOGITS
    ivity
    0.18
    ivities
    0.16
    swith
    0.13
    sWith
    0.13
    ively
    0.12
    ive
    0.12
    ividad
    0.11
    ype
    0.10
    ivist
    0.10
    IVITY
    0.10
    Activations Density 0.091%

    No Known Activations