© 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. 36273
    Prev
    Next
    INDEX
    Explanations

    people in surveys

    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
    nej
    -0.10
    ISH
    -0.08
    ãģĹãģ¦ãģĬãģı
    -0.08
    æľįåĬ¡äºİ
    -0.08
    unes
    -0.08
    andle
    -0.08
    ish
    -0.08
    áĢĤ
    -0.08
    è¿Ļå¥Ĺ
    -0.07
     Spi
    -0.07
    POSITIVE LOGITS
    åĽ¡
    0.11
    å®Įæ¯ķ
    0.10
    æĪ¡
    0.10
    è¦ģä¹Ī
    0.10
    æĤłæĤł
    0.10
    欢åĸľ
    0.09
    çĤ¹å¤´
    0.09
    _EVT
    0.09
    ä¸įçŁ¥ä¸įè§ī
    0.09
    éĹº
    0.09
    Activations Density 0.242%

    No Known Activations