© 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. 34627
    Prev
    Next
    INDEX
    Explanations

    experiences of distress and identity

    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
    å¼ĢåĪĽ
    -0.09
     Carrier
    -0.09
    ä¸įåĬ¨
    -0.09
     дÑĥÑħ
    -0.08
     ej
    -0.08
    .Dispatch
    -0.08
    åĢĻ
    -0.08
    deliver
    -0.08
    ä¸įåıĬ
    -0.08
    å¥Ķè·ij
    -0.08
    POSITIVE LOGITS
    icits
    0.09
    æ±ĤåĬ©
    0.09
    èĩªåĬ©
    0.09
    æĬķ注
    0.09
    antasy
    0.08
    ayar
    0.08
    è´¬
    0.08
    æĿ¥è®¿
    0.08
    ä½ĵéªĮ
    0.08
    _PP
    0.08
    Activations Density 0.187%

    No Known Activations