© 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. 38582
    Prev
    Next
    INDEX
    Explanations

    foresee and predict future

    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
    icans
    -0.10
    åIJİèĢħ
    -0.09
    ç´¯äºĨ
    -0.09
    ä½Ĩè¿Ļ
    -0.09
    upal
    -0.09
    ilon
    -0.09
    毫ä¸įçĬ¹è±«
    -0.09
    ç´Ĭä¹±
    -0.09
    uria
    -0.09
    å¦ĵ
    -0.09
    POSITIVE LOGITS
    ably
    0.10
    èĮĦ
    0.09
    涧
    0.09
    ве
    0.08
    rest
    0.08
    ermen
    0.08
    åķĨæľº
    0.08
    ä¸ĢäºĮ
    0.08
     Garc
    0.08
     обÑĢазом
    0.08
    Activations Density 0.008%

    No Known Activations