© 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. 2361
    Prev
    Next
    INDEX
    Explanations

    photo metadata and sharing services

    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
    /xhtml
    -0.08
     Gros
    -0.08
    issuer
    -0.08
    å¤ĩ
    -0.08
    ç¾Ŀ
    -0.08
    åĬ¨éĿĻ
    -0.08
    å¤ĩçĶ¨
    -0.08
    æ·±åħ¥
    -0.07
    Advertisement
    -0.07
    rift
    -0.07
    POSITIVE LOGITS
    albums
    0.11
    åĭĥåĭĥ
    0.10
    æĻĴ
    0.09
    ocr
    0.09
    èµı
    0.09
    使çĶ¨æĿĥ
    0.09
    èµıæŀIJ
    0.09
    sharing
    0.09
    æīĺ管
    0.09
    .Params
    0.09
    Activations Density 0.049%

    No Known Activations