© 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. 2709
    Prev
    Next
    INDEX
    Explanations

    underneath or underlying meanings

    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
    沿çĿĢ
    -0.10
    åħŃåIJĪ
    -0.09
    注æĦıåĬĽ
    -0.09
    çħĮ
    -0.09
    óc
    -0.09
    åĽ´
    -0.09
     лиÑĩно
    -0.09
    iol
    -0.08
    .watch
    -0.08
    èĹ¿
    -0.08
    POSITIVE LOGITS
     underlying
    0.17
     underneath
    0.16
    åľ¨éĩĮéĿ¢
    0.14
    neath
    0.13
     Bene
    0.13
     beneath
    0.12
    åºķå±Ĥ
    0.11
    (hidden
    0.11
     behind
    0.11
     hidden
    0.11
    Activations Density 0.102%

    No Known Activations