© 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. 27530
    Prev
    Next
    INDEX
    Explanations

    pronouns

    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
    为åħ¶
    -0.10
    让å®ĥ
    -0.10
    åį«
    -0.10
    perc
    -0.09
    è¡Ľ
    -0.09
    enc
    -0.09
    otts
    -0.09
    san
    -0.09
    è·Łä»ĸ
    -0.09
    ä»°
    -0.09
    POSITIVE LOGITS
    odem
    0.09
    æģ¯æģ¯
    0.08
    åĥļ
    0.08
    éĻ¢éĻ¢éķ¿
    0.08
     own
    0.08
     Own
    0.08
    迦
    0.08
    loth
    0.08
    èĪĪ
    0.08
    \/
    0.08
    Activations Density 0.212%

    No Known Activations