© 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. 2238
    Prev
    Next
    INDEX
    Explanations

    premature birth, death, or end

    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
    åĩĨæŶ
    -0.11
    /view
    -0.10
    ots
    -0.09
    otts
    -0.09
    omens
    -0.09
    å¾Īæ¸ħæ¥ļ
    -0.09
    ething
    -0.09
    ä¸įæŃ¢
    -0.09
    .Paint
    -0.09
    髹
    -0.09
    POSITIVE LOGITS
    ities
    0.09
    ternal
    0.09
    /in
    0.09
    zeitig
    0.08
    cht
    0.08
    /il
    0.08
    èĻij
    0.08
    æĥ³æĥ³
    0.08
    idad
    0.08
     Ñģобой
    0.07
    Activations Density 0.014%

    No Known Activations