© 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. 63646
    Prev
    Next
    INDEX
    Explanations

    comparative outcomes

    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
    ä¸ĢåĪĨ
    -0.10
    å¤©åľ°
    -0.09
    _inputs
    -0.09
    失信
    -0.09
    .Requires
    -0.08
    天èµĭ
    -0.08
    ä¼ļå¼ķèµ·
    -0.08
    åŁºæķ°
    -0.08
    POSIT
    -0.08
    è¾ľè´Ł
    -0.08
    POSITIVE LOGITS
     overall
    0.10
    ãģĦãģıãģ¤ãģĭ
    0.09
     participant
    0.09
    åıĤä¸İèĢħ
    0.09
    å®īçĦ¶
    0.09
    表çİ°åĩº
    0.09
    åĽŀå¿Ĩ
    0.08
     Guaranteed
    0.08
    aN
    0.08
     conflic
    0.08
    Activations Density 0.817%

    No Known Activations