© 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. 31706
    Prev
    Next
    INDEX
    Explanations

    places and locations

    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
    çŨ
    -0.09
    etur
    -0.08
     Tay
    -0.08
    èļĮ
    -0.08
    -bot
    -0.08
     Afr
    -0.08
    kart
    -0.08
    è·£
    -0.07
     Mueller
    -0.07
     ont
    -0.07
    POSITIVE LOGITS
    é¹Ĭ
    0.09
    unei
    0.09
    воÑĢ
    0.09
     ÑĢей
    0.09
    æµģä¼ł
    0.09
    .Inject
    0.09
    uling
    0.09
    åµĺ
    0.09
    ween
    0.09
    atan
    0.09
    Activations Density 0.022%

    No Known Activations