© 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. 7214
    Prev
    Next
    INDEX
    Explanations

    Nielsen Ratings, SoundScan, Media

    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
    æĬ¥éħ¬
    -0.09
    shire
    -0.08
    ones
    -0.08
    æ·±å¤Ħ
    -0.08
    sWith
    -0.08
    spread
    -0.08
    sp
    -0.08
    ipe
    -0.08
     Whale
    -0.08
    tober
    -0.07
    POSITIVE LOGITS
    ç¬ı
    0.10
    TÄ°
    0.10
    声åĵį
    0.09
    éļ¾åıĹ
    0.09
    zig
    0.09
    æĹłå£°
    0.09
    è¿Ļå¼ł
    0.09
    viron
    0.09
    趸
    0.09
     Derrick
    0.09
    Activations Density 0.004%

    No Known Activations