© 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. 32546
    Prev
    Next
    INDEX
    Explanations

    pronouns and verbs

    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
    åľ¨æĪijçļĦ
    -0.07
    æľĢåIJİä¸Ģ
    -0.07
    éģĵå¾·
    -0.07
    An
    -0.07
    çĶŁåij½
    -0.07
    è¶ĭ
    -0.07
    .telegram
    -0.07
    åľ¨æĪij
    -0.07
    rette
    -0.07
    çļĦæľĢåIJİä¸Ģ
    -0.07
    POSITIVE LOGITS
     them
    0.13
    å®ĥ们
    0.12
    她们
    0.11
     us
    0.11
     ниÑħ
    0.11
     Ñģобой
    0.11
    /from
    0.11
    æĪijåĢij
    0.10
    ä»ĸåĢij
    0.10
    \Eloquent
    0.10
    Activations Density 0.075%

    No Known Activations