© 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. 2185
    Prev
    Next
    INDEX
    Explanations

    election 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
    .Merge
    -0.10
    å°ijåIJĥ
    -0.10
    ä»İ严治
    -0.09
    еÑģп
    -0.09
    Pixmap
    -0.09
    unt
    -0.09
    å¾Ĺèµ·
    -0.09
    åıijå±ķ空éĹ´
    -0.09
     prox
    -0.09
    é¢ł
    -0.09
    POSITIVE LOGITS
    åºŁçī©
    0.08
    å´©æºĥ
    0.08
     Shall
    0.08
    æݨåIJij
    0.08
     Sweep
    0.08
     overst
    0.08
    IRA
    0.07
    ienza
    0.07
    åĮ»éĻ¢
    0.07
     employment
    0.07
    Activations Density 0.137%

    No Known Activations