© 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. 57562
    Prev
    Next
    INDEX
    Explanations

    election votes

    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
    ieri
    -0.11
    æĸ©
    -0.11
    æĸĭ
    -0.10
    æŀ¶
    -0.10
    åĪĽæĸ°èĥ½åĬĽ
    -0.09
    çĶij
    -0.09
    æ±²
    -0.09
     SÅĤow
    -0.09
    CLAIM
    -0.09
    -equiv
    -0.09
    POSITIVE LOGITS
     паÑĢÑĤи
    0.09
    vio
    0.09
    éħ¬
    0.09
    uner
    0.08
    åĺ´å·´
    0.08
    åīįåı°
    0.08
     élect
    0.08
    æĶ¶
    0.08
    ç»ĵæĻ¶
    0.08
    Elect
    0.08
    Activations Density 0.286%

    No Known Activations