© 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. 18072
    Prev
    Next
    INDEX
    Explanations

    host

    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
    éĺ
    -0.11
    æĶ¾å¼ĥ
    -0.09
    ç¼ĿéļĻ
    -0.09
    æŶæĬ¥
    -0.08
    æ³·
    -0.08
    åľ³
    -0.08
    åĬŀæ¡Ī
    -0.08
    ä¸įèĤ¯
    -0.08
     Romance
    -0.08
     unread
    -0.08
    POSITIVE LOGITS
     host
    0.13
    -host
    0.12
    /host
    0.12
    host
    0.11
    (host
    0.11
     Host
    0.10
     hosts
    0.10
    .Host
    0.10
    宿
    0.10
    .host
    0.10
    Activations Density 0.043%

    No Known Activations