© 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. 2257
    Prev
    Next
    INDEX
    Explanations

    itself, themselves, ourselves, herself

    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
    ensi
    -0.09
    -Nazi
    -0.08
    çļĦè¡£æľį
    -0.08
    -Za
    -0.08
    å°ı康
    -0.08
    unny
    -0.08
    çIJ
    -0.08
    _EV
    -0.08
    ItemCount
    -0.08
    ắm
    -0.08
    POSITIVE LOGITS
     itself
    0.23
    æľ¬èº«çļĦ
    0.22
    æľ¬èº«
    0.21
    èĩªèº«
    0.21
    èĩªèº«çļĦ
    0.21
     themselves
    0.21
    ä»ĸèĩªå·±
    0.20
     ourselves
    0.19
    èĩªå·±
    0.18
     herself
    0.18
    Activations Density 0.068%

    No Known Activations