© 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. 50319
    Prev
    Next
    INDEX
    Explanations

    cameo, appearance, chameleon, egg

    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
    ament
    -0.10
    inct
    -0.09
    liness
    -0.09
    lut
    -0.09
    ively
    -0.09
    广大å¸Ĥæ°ij
    -0.09
    rise
    -0.08
    æ±
    -0.08
    éļľ
    -0.08
    ismo
    -0.08
    POSITIVE LOGITS
    plex
    0.10
    æĮĤéĴ©
    0.09
    æ³¼
    0.09
    åķĥ
    0.08
    kest
    0.08
    uez
    0.08
    å¾ģæ±Ĥ
    0.08
    agic
    0.08
    ously
    0.08
    ilan
    0.08
    Activations Density 0.002%

    No Known Activations