© 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. 56250
    Prev
    Next
    INDEX
    Explanations

    Liberation of, insomnia, Nation, Contemporary Art, CONTRACT, Antarctic Names, Freedom of, Bar Association

    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
    iage
    -0.10
    çĮ©
    -0.10
    æįı
    -0.09
    ITAL
    -0.09
    ayah
    -0.09
    _DISP
    -0.09
    åºŀ
    -0.09
    æ¥Ķ
    -0.09
    è£
    -0.09
    pire
    -0.09
    POSITIVE LOGITS
    为主é¢ĺçļĦ
    0.09
    è¿ĺä¸į
    0.09
    åľ¨æĪij
    0.09
    ç®Ģ称
    0.09
    åĽłä¸ºæĪij
    0.08
    æĪijè¿ĺæĺ¯
    0.08
    åģ¥åº·åıijå±ķ
    0.08
    soever
    0.08
     пÑĢоÑģмоÑĤÑĢ
    0.08
    ToFile
    0.07
    Activations Density 0.402%

    No Known Activations