© 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. 1459
    Prev
    Next
    INDEX
    Explanations

    prophecy / prophylactic

    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§ŀ
    -0.09
    çªģå¦Ĥåħ¶æĿ¥
    -0.08
    åį¦
    -0.08
    uper
    -0.08
    boss
    -0.08
    borg
    -0.08
     boss
    -0.08
    lo
    -0.08
    лик
    -0.08
    olum
    -0.08
    POSITIVE LOGITS
    omic
    0.11
    å·²ä¹ħçļĦ
    0.10
    å·²ä¹ħ
    0.10
    èĢħçļĦ
    0.09
    mere
    0.09
    edly
    0.09
    виÑĤ
    0.09
    åıĹçĽĬ
    0.09
    äºĨå¤ļå°ij
    0.09
    沫
    0.09
    Activations Density 0.009%

    No Known Activations