© 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. 58490
    Prev
    Next
    INDEX
    Explanations

    dynamic data parameter url

    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
    ÑĪив
    -0.08
     Franken
    -0.08
    _tpl
    -0.08
    帽
    -0.08
    arus
    -0.08
    çĴŁ
    -0.08
    athom
    -0.08
    ered
    -0.08
    åİŁå§ĭ
    -0.08
    nano
    -0.08
    POSITIVE LOGITS
    åĬ¨æĢģ
    0.17
    (dynamic
    0.17
    .Dynamic
    0.16
    dynamic
    0.15
     dynamic
    0.15
    .dynamic
    0.14
    _dynamic
    0.13
     dynam
    0.13
    ä¸įå®ī
    0.13
    Dynamic
    0.12
    Activations Density 0.152%

    No Known Activations