© 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. 9857
    Prev
    Next
    INDEX
    Explanations

    accommodation details

    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
    羸
    -0.09
    åĶ¾
    -0.09
    .jpg
    -0.09
    ber
    -0.09
    åĿĩè¡¡
    -0.09
    纥
    -0.09
    å¾Ĵ
    -0.09
     Steele
    -0.09
    ophil
    -0.09
    èĦ¸
    -0.09
    POSITIVE LOGITS
    客æĪ¿
    0.10
     consul
    0.10
    åĩºç§Ł
    0.10
     Pillow
    0.09
    æīĢè°ĵ
    0.09
    ambre
    0.09
     Microwave
    0.08
    TW
    0.08
    van
    0.08
    è¿ģ
    0.08
    Activations Density 0.096%

    No Known Activations