© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21391
    Prev
    Next
    INDEX
    Explanations

    FILE or IRE markers

    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
    ç¬ijäºĨ
    -0.12
    æµģè¡Į
    -0.11
    ç´¯äºĨ
    -0.11
    çľĭäºĨ
    -0.10
    COPE
    -0.10
    åĢį
    -0.10
    åłĤ
    -0.09
     Learned
    -0.09
    .ham
    -0.09
    otron
    -0.09
    POSITIVE LOGITS
    buzz
    0.08
    åIJ¹
    0.08
    Re
    0.07
    >>>
    0.07
    er
    0.07
    ä¸Ĭä¸ĭ
    0.07
    brick
    0.07
    à®´
    0.07
    idis
    0.07
    nt
    0.07
    Activations Density 0.006%

    No Known Activations