© 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. 4872
    Prev
    Next
    INDEX
    Explanations

    warrant

    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
    è§Ħ
    -0.08
    é²ł
    -0.08
    omm
    -0.08
    hen
    -0.08
    loth
    -0.08
    ponsored
    -0.08
    åķĸ
    -0.08
    å°ijè§ģ
    -0.08
    arus
    -0.08
    per
    -0.08
    POSITIVE LOGITS
    edException
    0.10
    象
    0.09
    æľ¬ç½ij
    0.09
    á¹Ń
    0.09
    æķij人
    0.08
    zos
    0.08
    rawid
    0.08
    æĭ¿ä¸ĭ
    0.08
    èķĻ
    0.08
    å¬ĸ
    0.08
    Activations Density 0.006%

    No Known Activations