© 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. 10775
    Prev
    Next
    INDEX
    Explanations

    domain extensions and paths

    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
    нÑĤеÑĢ
    -0.10
     деÑĢ
    -0.09
    _PG
    -0.09
     Opr
    -0.09
     Affero
    -0.08
    IOUS
    -0.08
    çºł
    -0.08
    ailer
    -0.08
    imet
    -0.08
    ä¼IJ
    -0.08
    POSITIVE LOGITS
    év
    0.10
     Towers
    0.09
    èĩªè§ī
    0.08
    anto
    0.08
    casting
    0.08
     дела
    0.08
    èĥİ
    0.08
    ä¸İåħ¶ä»ĸ
    0.08
    滹
    0.08
    å°ı康社ä¼ļ
    0.08
    Activations Density 0.088%

    No Known Activations