© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52371
    Prev
    Next
    INDEX
    Explanations

    Jesus Christ

    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
    èĩªåĪ¶
    -0.10
    æĹłå½¢
    -0.09
    æŃĻ
    -0.09
    ä¸ĵ
    -0.09
    æµģ转
    -0.09
     Cummings
    -0.09
    PURE
    -0.09
    phem
    -0.08
    纯粹
    -0.08
    ember
    -0.08
    POSITIVE LOGITS
    æĭ¯æķij
    0.11
    åĬŁåĬ³
    0.10
    èĢ¶ç¨£
    0.10
    çīºçī²
    0.10
    çīº
    0.10
    6
    0.09
    .RESET
    0.09
    7
    0.09
    çĶ¨å¾®ä¿¡
    0.09
    ä»·éĴ±
    0.09
    Activations Density 0.026%

    No Known Activations