© 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. 10971
    Prev
    Next
    INDEX
    Explanations

    bedtime story or book

    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
    .vo
    -0.10
     vo
    -0.10
    粪
    -0.09
    ä¸Ģå¿ĥ
    -0.09
    oric
    -0.09
    ivant
    -0.09
    åIJĿ
    -0.09
    vo
    -0.09
    (vo
    -0.09
    ÑĤÑĮ
    -0.09
    POSITIVE LOGITS
    çĿ¡åīį
    0.14
    æŀķ
    0.12
     bedtime
    0.11
    åĵĦ
    0.11
    æŀķ头
    0.10
     nightly
    0.09
    ä¾ĭè¡Į
    0.09
    çĨĦ
    0.09
     promise
    0.08
    温馨
    0.08
    Activations Density 0.036%

    No Known Activations