© 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. 62772
    Prev
    Next
    INDEX
    Explanations

    superhero or hero

    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
    ings
    -0.10
    OrCreate
    -0.10
    enen
    -0.10
    exclusive
    -0.10
    ãģĵãģ¨
    -0.09
    customers
    -0.08
     Geneva
    -0.08
    ка
    -0.08
    è¿Ļå°±
    -0.08
    urgeon
    -0.08
    POSITIVE LOGITS
    arend
    0.10
    avn
    0.10
    anded
    0.10
    ously
    0.09
    ocratic
    0.09
    ues
    0.09
    aceous
    0.09
    شع
    0.09
    ä¾Ī
    0.09
    å½Ģ
    0.09
    Activations Density 0.011%

    No Known Activations