© 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. 32405
    Prev
    Next
    INDEX
    Explanations

    guru of leadership

    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
    mere
    -0.09
    onn
    -0.08
    åĬ¡å·¥
    -0.08
    ynn
    -0.08
    raj
    -0.08
     entirety
    -0.08
    -thirds
    -0.08
    å·ŀ
    -0.08
    lah
    -0.08
    Ñģ
    -0.08
    POSITIVE LOGITS
    ç²²
    0.12
    çĪ·
    0.11
    plex
    0.11
    们çļĦ
    0.10
    ugu
    0.10
    èĿ®
    0.10
    æĮĩ导ä¸ĭ
    0.10
    èĬ¨
    0.10
    ues
    0.09
    ðŁı»
    0.09
    Activations Density 0.008%

    No Known Activations