© 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. 10627
    Prev
    Next
    INDEX
    Explanations

    help, save, get, keep, powered

    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
    _inputs
    -0.10
    aska
    -0.10
    maal
    -0.09
    å°±å¿ħé¡»
    -0.09
     Affero
    -0.09
    Ñħи
    -0.09
    æĤ²è§Ĥ
    -0.09
    ogany
    -0.08
    atti
    -0.08
     MONEY
    -0.08
    POSITIVE LOGITS
    帮åĬ©
    0.11
    æĭ¯æķij
    0.11
    帮åĬ©ä¼ģä¸ļ
    0.11
    å¸®ä½ł
    0.10
    æĮ¯åħ´
    0.10
    带æĿ¥æĽ´å¤ļ
    0.10
    å¸¦ä½ł
    0.10
    åĬ©åĬĽ
    0.10
    help
    0.10
    åħ´æĹº
    0.10
    Activations Density 0.110%

    No Known Activations