© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8558
    Prev
    Next
    INDEX
    Explanations

    3M/3T3/3F4/3SDES

    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
     Roberto
    -0.08
    пиÑĤ
    -0.08
    ertation
    -0.08
    ONO
    -0.08
    å¨Ĩ
    -0.08
    å¿ĺ
    -0.08
    æľºä½ĵ
    -0.08
    LERÄ°
    -0.07
    Jur
    -0.07
    _IB
    -0.07
    POSITIVE LOGITS
    åĩı
    0.11
    /desktop
    0.10
    éģIJ
    0.10
    æīĵåį¡
    0.09
    é¼¾
    0.09
    æ¸Ľ
    0.09
    æ°ĶåĢĻåıĺåĮĸ
    0.08
    bic
    0.08
    aday
    0.08
    失åĪ©
    0.08
    Activations Density 0.041%

    No Known Activations