© 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. 51216
    Prev
    Next
    INDEX
    Explanations

    -en parts of words

    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
     Ñģобой
    -0.13
    aned
    -0.09
    æijĪ
    -0.09
    å¯¹æľªæĿ¥
    -0.09
    \<^
    -0.09
    zelf
    -0.09
    cip
    -0.09
    _ptrs
    -0.09
    _CONFIGURATION
    -0.08
    enet
    -0.08
    POSITIVE LOGITS
    ness
    0.12
    ingly
    0.09
    èµĦæºIJä¼ĺåĬ¿
    0.09
    æĦıä¹īä¸ĬçļĦ
    0.09
    mill
    0.09
    thal
    0.09
    sure
    0.08
    诮
    0.08
    s
    0.08
     dvd
    0.08
    Activations Density 0.015%

    No Known Activations