© 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. 21427
    Prev
    Next
    INDEX
    Explanations

    Battlestar Galactica

    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
    odal
    -0.09
    åĵĤ
    -0.09
    èģĶæĥ³
    -0.08
    绿水
    -0.08
    éĽ¾
    -0.08
    主æµģ
    -0.08
    å¹Ħ
    -0.08
    ìĭ¬
    -0.08
    æĻ®éģį
    -0.08
    roz
    -0.08
    POSITIVE LOGITS
    _pas
    0.09
    èĮ¬
    0.09
    ationToken
    0.09
    æķĸ
    0.09
     Duck
    0.09
    Beer
    0.08
    ç¾Ĭæ¯Ľ
    0.08
    .mods
    0.08
    NewLabel
    0.08
    ắc
    0.08
    Activations Density 0.004%

    No Known Activations