© 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. 6479
    Prev
    Next
    INDEX
    Explanations

    headlines and titles

    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
    åīį身
    -0.09
    èµŀèµı
    -0.09
    èĭ¥å¹²
    -0.09
    éĽĨåĽ¢èĤ¡ä»½
    -0.09
    ç»Ĩå¿ĥ
    -0.09
    setStatus
    -0.09
    åĽŀé¦Ī
    -0.09
    decess
    -0.09
    éħįèµĦ
    -0.08
    otted
    -0.08
    POSITIVE LOGITS
     headline
    0.20
     headlines
    0.17
    æłĩé¢ĺ
    0.16
     sensational
    0.14
    headline
    0.14
    æĸ°éĹ»
    0.13
    ãĤ¿ãĤ¤ãĥĪãĥ«
    0.12
    .getTitle
    0.12
     title
    0.11
    >Title
    0.11
    Activations Density 0.114%

    No Known Activations