© 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. 53983
    Prev
    Next
    INDEX
    Explanations

    Robinson or Roberto names

    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
    ences
    -0.11
    iness
    -0.10
    ance
    -0.09
    reas
    -0.09
    unce
    -0.09
    ıyla
    -0.09
    ud
    -0.09
    ulty
    -0.09
    累累
    -0.09
    ãĥĪãĥª
    -0.09
    POSITIVE LOGITS
     Ñģебе
    0.11
    ãģĹãģ¾ãģĦ
    0.11
    å¨ĺ
    0.10
    ï¸
    0.09
    çŀ©
    0.09
    çŀ©çĽ®
    0.08
    ãģ®ãģ§
    0.08
    iÄĻ
    0.08
    esse
    0.08
    ç´łåħ»
    0.08
    Activations Density 0.020%

    No Known Activations