© 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. 22632
    Prev
    Next
    INDEX
    Explanations

    high vacuum

    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
    æł²
    -0.09
    åĩ½
    -0.09
    æ°´åŁŁ
    -0.09
    plets
    -0.09
    usercontent
    -0.09
    èı±
    -0.09
     оÑĤз
    -0.08
    éĽ¨æ°´
    -0.08
    è¶Ĭ
    -0.08
    -flag
    -0.08
    POSITIVE LOGITS
    大ä¼Ĺ
    0.11
    åĿŀ
    0.11
    å°ģéĹŃ
    0.10
    çľŁç©º
    0.10
    å½ĵæŶçļĦ
    0.09
    åĦĴ
    0.09
    metry
    0.09
    anes
    0.09
    é£Ļ
    0.09
    igar
    0.09
    Activations Density 0.113%

    No Known Activations