© 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. 4842
    Prev
    Next
    INDEX
    Explanations

    granuloma formation

    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
    责任ç¼ĸè¾ij
    -0.10
    骸
    -0.10
     ×IJש
    -0.09
    liness
    -0.09
    åĴĴ
    -0.09
    éŀŃ
    -0.09
    çĶ³è¯ī
    -0.09
    åı¯æĥ³èĢĮçŁ¥
    -0.09
    oure
    -0.08
    iei
    -0.08
    POSITIVE LOGITS
    ikan
    0.09
    adb
    0.09
    éĿ¢ä¸Ĭ
    0.09
    åħ³éĶ®
    0.08
    jal
    0.08
    cle
    0.08
    finity
    0.08
    lt
    0.08
    ERO
    0.08
    å±±ä¸Ĭ
    0.08
    Activations Density 0.004%

    No Known Activations