© 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. 4216
    Prev
    Next
    INDEX
    Explanations

    imminent departure and logistical information

    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
    less
    -0.09
    urette
    -0.09
    ening
    -0.09
    åį·
    -0.08
    hurst
    -0.08
    asco
    -0.08
    ega
    -0.08
    糸
    -0.08
    <Any
    -0.08
    æĻĤçĤ¹ãģ§
    -0.08
    POSITIVE LOGITS
    ä¹Łå¸ĮæľĽ
    0.10
    屿
    0.10
    .geom
    0.09
    æ¡¢
    0.09
    æŃ¥éª¤
    0.09
    apes
    0.09
    templ
    0.09
    åĩłä½ķ
    0.09
    dbname
    0.09
    .inc
    0.09
    Activations Density 0.004%

    No Known Activations