© 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. 34328
    Prev
    Next
    INDEX
    Explanations

    names and compound words with "-back"

    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
    Ëī
    -0.10
    oni
    -0.10
    æ¡İ
    -0.09
    è¦ģ说
    -0.09
    tas
    -0.08
    å¸Ĥåħ¬å®īå±Ģ
    -0.08
    æĪIJç«ĭäºĨ
    -0.08
    ragments
    -0.08
    cher
    -0.08
    ilder
    -0.08
    POSITIVE LOGITS
    é«ĺåİŁ
    0.09
     é»
    0.09
    _ack
    0.08
    ãģ¨æĢĿãģ£ãģ¦ãģĦãģŁ
    0.08
    对æѤ
    0.08
    erule
    0.08
    éļıå¤Ħ
    0.08
    OfSize
    0.08
    绩
    0.08
     plateau
    0.08
    Activations Density 0.021%

    No Known Activations