© 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. 22480
    Prev
    Next
    INDEX
    Explanations

    found that

    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¿»
    -0.10
    erno
    -0.10
     Ñģобой
    -0.10
    å¡«
    -0.09
    æľ¬èº«çļĦ
    -0.09
    ç²Ł
    -0.09
    poi
    -0.09
    ewn
    -0.09
    å¹´é¾Ħ段
    -0.09
    éģĺ
    -0.09
    POSITIVE LOGITS
     rằng
    0.10
    ings
    0.10
    æĻĸ
    0.09
     no
    0.09
    ampa
    0.09
    åıªè¦ģæĺ¯
    0.08
     Viol
    0.08
    请çĤ¹åĩ»
    0.08
    顾
    0.08
     dolayı
    0.08
    Activations Density 0.055%

    No Known Activations