© 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. 50237
    Prev
    Next
    INDEX
    Explanations

    Democrats and Democratic actions

    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
    åľī
    -0.09
    款
    -0.09
    æĸ°è¥¿
    -0.09
     Cla
    -0.09
    åī§
    -0.08
     pros
    -0.08
     fame
    -0.08
    åIJįæ°Ķ
    -0.08
    çĻ½é©¬
    -0.08
    Accessor
    -0.08
    POSITIVE LOGITS
    CTS
    0.10
    bara
    0.09
    èĪĽ
    0.09
    赡
    0.09
    onga
    0.09
    ä½ĵè´´
    0.08
    å£ħ
    0.08
    æ¶Ķ
    0.08
    rones
    0.08
    /rs
    0.08
    Activations Density 0.027%

    No Known Activations