© 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. 38691
    Prev
    Next
    INDEX
    Explanations

    should be

    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
    é©¿
    -0.10
    ilver
    -0.08
    缼è¡Į
    -0.08
    xCD
    -0.08
    èķī
    -0.08
    åĪĿæľŁ
    -0.08
    åIJĦ项
    -0.07
    Ñijм
    -0.07
    çĭŀ
    -0.07
    ervices
    -0.07
    POSITIVE LOGITS
    ä¹Łåıªèĥ½
    0.12
    è¶³å¤ŁçļĦ
    0.10
    æijĪ
    0.10
    udos
    0.10
    ewise
    0.10
    éº»æľ¨
    0.10
    ä¸ĭæīĭ
    0.09
    atcher
    0.09
    å¿ħå¤ĩ
    0.09
    å°±å¿ħé¡»
    0.09
    Activations Density 0.066%

    No Known Activations