© 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. 26690
    Prev
    Next
    INDEX
    Explanations

    names of people

    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
    gte
    -0.10
    isu
    -0.09
    [color
    -0.09
    ulus
    -0.08
    otto
    -0.08
    å¤ļ彩
    -0.08
    asure
    -0.08
     chẳng
    -0.08
    -bodied
    -0.08
    sWith
    -0.08
    POSITIVE LOGITS
    hiro
    0.09
     полов
    0.09
     Sergey
    0.09
    ãģªãģıãģ¦
    0.09
    è¾ħ导åijĺ
    0.09
    éªħ
    0.09
     иÑģÑĤ
    0.09
    theless
    0.09
    UNE
    0.08
    å¥ģ
    0.08
    Activations Density 0.023%

    No Known Activations