© 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. 33667
    Prev
    Next
    INDEX
    Explanations

    a/an followed by a singular noun

    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
    å½ĵæĪIJ
    -0.11
    æľªæĪIJ
    -0.10
    çļĦ人çī©
    -0.10
    ideas
    -0.10
    ä¿ĿéĻ©åħ¬åı¸
    -0.10
    åģļ人
    -0.09
    itness
    -0.09
    人çī©
    -0.09
    SURE
    -0.09
     getchar
    -0.09
    POSITIVE LOGITS
    ecz
    0.09
    èħ¥
    0.08
    级以ä¸Ĭ
    0.08
    ting
    0.08
    wald
    0.08
    ted
    0.08
    åĽŀæĬ¥
    0.08
     Blond
    0.07
    对ç«ĭ
    0.07
     bang
    0.07
    Activations Density 0.035%

    No Known Activations