© 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. 30565
    Prev
    Next
    INDEX
    Explanations

    game-maker, video-game engines, mods, editing

    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
    IBM
    -0.09
    articles
    -0.09
    WS
    -0.09
    éĹ®è¯¢
    -0.09
    RP
    -0.09
    imens
    -0.09
    Ws
    -0.09
     Kv
    -0.09
    fcn
    -0.09
    _ws
    -0.09
    POSITIVE LOGITS
    InBackground
    0.09
    缸çĪ±
    0.08
    离
    0.08
    èĩªåĪ¶
    0.08
    ä¸Ģ缴æĺ¯
    0.08
     Ча
    0.08
     VÅ©
    0.08
    æį£
    0.08
    ground
    0.08
     ho
    0.07
    Activations Density 0.152%

    No Known Activations