© 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. 61585
    Prev
    Next
    INDEX
    Explanations

    elder care

    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
    illion
    -0.09
    ugen
    -0.09
    elli
    -0.09
    çݯèĬĤ
    -0.09
    æĬ±
    -0.09
    æĥĬ
    -0.09
    æ¯Ķçī¹
    -0.09
    æĭĽå¾ħ
    -0.08
    ¤
    -0.08
    asso
    -0.08
    POSITIVE LOGITS
    iges
    0.10
    fully
    0.09
    iegel
    0.09
    istry
    0.09
    ually
    0.09
    ding
    0.09
    RIES
    0.08
    zÄħ
    0.08
    chaft
    0.08
    IES
    0.08
    Activations Density 0.018%

    No Known Activations