© 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. 35942
    Prev
    Next
    INDEX
    Explanations

    ambition and feasibility of goals

    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
     Arrow
    -0.10
    arrow
    -0.10
    缺失
    -0.09
    èĬĿ
    -0.09
    è¯ķéªĮåĮº
    -0.09
     arrow
    -0.08
    æµģåIJij
    -0.08
    èĹĵ
    -0.08
    Arrow
    -0.08
    usk
    -0.08
    POSITIVE LOGITS
     realistic
    0.17
    åı¯è¡Į
    0.15
     unrealistic
    0.15
    åı¯è¡ĮæĢ§
    0.14
     realistically
    0.14
    çIJĨæĥ³
    0.12
     realism
    0.12
    æĺ¯ä¸įåı¯èĥ½
    0.12
    éĩİå¿ĥ
    0.12
    è¿ĩé«ĺ
    0.12
    Activations Density 0.208%

    No Known Activations