© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50885
    Prev
    Next
    INDEX
    Explanations

    followed by specific 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
    ongan
    -0.12
    æľīå¿ħè¦ģ
    -0.12
    ä¸ŃåĽ½çĶµä¿¡
    -0.11
    ä¸ŃåĽ½åı¤ä»£
    -0.11
    inha
    -0.10
    æѤ
    -0.10
    åĻĻ
    -0.10
    人士
    -0.10
    ä¸ŃåĽ½
    -0.10
    zeitig
    -0.09
    POSITIVE LOGITS
    standing
    0.19
     regard
    0.16
    stood
    0.15
     regards
    0.15
    holds
    0.14
    drawing
    0.13
    /by
    0.13
    held
    0.13
     respect
    0.13
    /from
    0.12
    Activations Density 0.580%

    No Known Activations