© 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. 39330
    Prev
    Next
    INDEX
    Explanations

    such officers, seam, restoration, information

    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
    çĿ¦
    -0.09
    mega
    -0.09
    landers
    -0.08
    éĬ®
    -0.08
    üt
    -0.08
    æijĨåľ¨
    -0.08
    æĪij们éĥ½
    -0.08
     Madden
    -0.08
    é¢ģ
    -0.08
    icle
    -0.08
    POSITIVE LOGITS
    é³į
    0.09
    ç¨İè´¹
    0.09
     amounts
    0.09
    认为
    0.09
    为æŃ¢
    0.09
    vak
    0.09
    itt
    0.08
    ä»ĸ认为
    0.08
    ãĤ¿ãĥ«
    0.08
    Ny
    0.08
    Activations Density 0.047%

    No Known Activations