© 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. 17797
    Prev
    Next
    INDEX
    Explanations

    open spaces and environments

    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
    rix
    -0.09
    ctor
    -0.08
    immer
    -0.08
    ata
    -0.08
     Saud
    -0.08
    we
    -0.08
    Unnamed
    -0.08
     Surveillance
    -0.08
    omer
    -0.07
    -lived
    -0.07
    POSITIVE LOGITS
    åĥı个
    0.11
    ãģ³
    0.09
    æģĥ
    0.09
    ï¸
    0.09
    åĨ³èĥľ
    0.08
    æĸ°æł¼å±Ģ
    0.08
    à¸ģาย
    0.08
    ä¹ĭ声
    0.08
    SIDE
    0.08
    çĶµå½±éĻ¢
    0.08
    Activations Density 0.007%

    No Known Activations