© 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. 18744
    Prev
    Next
    INDEX
    Explanations

    follow me

    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
    ifier
    -0.10
    uring
    -0.10
    erator
    -0.09
    ifying
    -0.09
    _Framework
    -0.08
    ạt
    -0.08
    lify
    -0.08
     Weiter
    -0.08
    ifa
    -0.08
    ull
    -0.08
    POSITIVE LOGITS
     dõi
    0.16
     closely
    0.12
    ings
    0.12
    ðŁı»
    0.11
    ÑģÑĤвие
    0.11
    -up
    0.11
    -ups
    0.11
    สà¸ļาย
    0.10
    è¹
    0.10
     Äijuá»ķi
    0.10
    Activations Density 0.088%

    No Known Activations