© 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. 7459
    Prev
    Next
    INDEX
    Explanations

    statement of responsibility

    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
    ä»Ģä¹Īéĥ½
    -0.12
    æ®ĥ
    -0.10
    coat
    -0.10
    媳
    -0.09
    strup
    -0.09
    åŀ©
    -0.09
    æ´¼
    -0.09
    æºı
    -0.09
     GPLv
    -0.08
    å¹³æ°ij
    -0.08
    POSITIVE LOGITS
    ¹
    0.09
    rô
    0.08
    åı¯éĿłçļĦ
    0.08
     آخر
    0.08
    ero
    0.08
    å¤ĩ
    0.08
    èĤ²
    0.08
    æ¿ij
    0.08
    ìĤ°ìĹħ
    0.08
     ÑģкаÑĩ
    0.08
    Activations Density 0.022%

    No Known Activations