© 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. 20316
    Prev
    Next
    INDEX
    Explanations

    path to

    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
    -0.08
    å´Ľ
    -0.08
    ÑģÑĤÑĢ
    -0.08
     digs
    -0.08
    ilate
    -0.08
    ste
    -0.08
     Doub
    -0.08
     Kendrick
    -0.08
    æķ¬çķı
    -0.08
    æł©
    -0.07
    POSITIVE LOGITS
    éĢĶ
    0.13
    æĽ²æĬĺ
    0.10
    诸èijĽ
    0.10
    ä¸įå°½
    0.10
    å±ħ室
    0.09
    ä¼ı
    0.09
    åĿİåĿ·
    0.09
    ogene
    0.09
    æĹİ
    0.09
    ä¸Ģä¸ĸ
    0.09
    Activations Density 0.028%

    No Known Activations