© 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. 7045
    Prev
    Next
    INDEX
    Explanations

    express certainty or opinion

    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
    èµĸ以
    -0.08
    edException
    -0.08
    对æīĭ
    -0.08
    ule
    -0.08
    leftright
    -0.07
    è°ľ
    -0.07
    è¿ĺæľīå¾Īå¤ļ
    -0.07
    unte
    -0.07
    çĶŁæĢķ
    -0.07
    aye
    -0.07
    POSITIVE LOGITS
    åı¯è¡ĮæĢ§
    0.18
    æıIJè®®
    0.17
    æıIJæ¡Ī
    0.17
    çļĦæĥ³æ³ķ
    0.17
    设æĥ³
    0.16
    æĥ³æ³ķ
    0.16
    åı¯è¡Į
    0.14
    çļĦåı¯èĥ½æĢ§
    0.13
     proposal
    0.13
    åı¯èĥ½æĢ§
    0.12
    Activations Density 0.310%

    No Known Activations