© 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. 62507
    Prev
    Next
    INDEX
    Explanations

    monthly intervals or increments

    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
    èIJİ缩
    -0.10
    åĨĴåĩº
    -0.10
    èĩ¼
    -0.09
    ç£ħ
    -0.09
    htable
    -0.09
    æķ°åįģ
    -0.09
    çģ«èĬ±
    -0.09
    è´³
    -0.09
    æīĢæľī人
    -0.09
    -Out
    -0.09
    POSITIVE LOGITS
     increments
    0.12
    ä¸ĢæŃ¥ä¸ĢæŃ¥
    0.12
     chunks
    0.12
     step
    0.11
    å¢ŀéĩı
    0.11
    increments
    0.11
    çļĦæŃ¥ä¼IJ
    0.10
    æī¹æ¬¡
    0.10
    chunks
    0.10
    æŃ¥éª¤
    0.10
    Activations Density 0.107%

    No Known Activations