© 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. 17167
    Prev
    Next
    INDEX
    Explanations

    quantity per unit

    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
    为æ°ij
    -0.10
    说起
    -0.08
    ness
    -0.08
    wk
    -0.08
    nt
    -0.08
    å¤Ł
    -0.08
     ÑģовÑģем
    -0.08
    _else
    -0.08
    第
    -0.08
    Asked
    -0.07
    POSITIVE LOGITS
    çħ
    0.10
    éĩį大
    0.10
    æĮ¹
    0.10
    åĨ³çŃĸéĥ¨ç½²
    0.10
    ober
    0.10
    cip
    0.09
    åľ¨æĦı
    0.09
    elson
    0.09
    æ²ĵ
    0.09
    /at
    0.09
    Activations Density 0.025%

    No Known Activations