© 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. 6432
    Prev
    Next
    INDEX
    Explanations

    can do or get something

    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
    åİī
    -0.09
    ä¿Ŀå®Ī
    -0.09
    _startup
    -0.09
    åݲ
    -0.08
    éģ½
    -0.08
    æľīä¸ĢçĤ¹
    -0.08
    åĩĽ
    -0.08
    ardy
    -0.08
    é¢ĩ为
    -0.08
    edom
    -0.08
    POSITIVE LOGITS
    éļıæŶéļıåľ°
    0.12
    åī©
    0.10
    éļıæŶ
    0.09
    ëħ¹
    0.09
    bao
    0.09
    åĨ³å®ļ
    0.08
    æ¸ļ
    0.08
    åıªåī©
    0.08
    Ñģи
    0.08
    JNI
    0.08
    Activations Density 0.002%

    No Known Activations