© 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. 33159
    Prev
    Next
    INDEX
    Explanations

    management consulting, software development

    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
    å¾Īä¸įéĶĻ
    -0.10
    ä»ĸè¿ĺ
    -0.09
    .createObject
    -0.09
    èļ¤
    -0.09
    æį·
    -0.09
    pire
    -0.09
    该æĿij
    -0.09
    ][/
    -0.09
    >>>>>>>
    -0.09
    éĵ³
    -0.09
    POSITIVE LOGITS
    /or
    0.16
     tháºŃm
    0.14
    çĶļèĩ³æĺ¯
    0.12
    çĶļèĩ³
    0.11
     etc
    0.11
     sometimes
    0.09
     optionally
    0.09
    以åıĬ
    0.09
    ãģĿãģĹãģ¦
    0.09
    以èĩ³äºİ
    0.08
    Activations Density 0.537%

    No Known Activations