© 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. 11651
    Prev
    Next
    INDEX
    Explanations

    pronouns and following verbs/nouns

    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
    .pet
    -0.08
    ores
    -0.08
    鹦
    -0.08
    裨
    -0.08
    ror
    -0.08
    åŀ¢
    -0.08
     Tes
    -0.08
    vs
    -0.08
    me
    -0.07
    hy
    -0.07
    POSITIVE LOGITS
    åIJİèĢħ
    0.14
    让她
    0.12
    让ä»ĸ
    0.11
    èĢģ人家
    0.11
    è®ĵä»ĸ
    0.11
    åijĬè¯īä»ĸ
    0.11
    åijĬè¯ī她
    0.10
    æĪıåī§
    0.10
    _HELPER
    0.10
    .cloudflare
    0.09
    Activations Density 0.184%

    No Known Activations