© 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. 35213
    Prev
    Next
    INDEX
    Explanations

    Billboard charts

    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
    erator
    -0.11
    æĦīå¿«
    -0.09
    ero
    -0.09
    lore
    -0.09
    lessly
    -0.09
    erate
    -0.09
    atoria
    -0.08
    uation
    -0.08
    ynet
    -0.08
    stead
    -0.08
    POSITIVE LOGITS
    sWith
    0.09
    åıijè¡Į人
    0.08
    åĸĻ
    0.08
    çĥ
    0.08
    alley
    0.08
    .scalar
    0.08
    éª
    0.08
    르
    0.08
     vigil
    0.08
    mé
    0.08
    Activations Density 0.002%

    No Known Activations