© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19412
    Prev
    Next
    INDEX
    Explanations

    Sony Pictures Entertainment

    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
     Lua
    -0.10
     lua
    -0.09
    Lua
    -0.09
    _loaded
    -0.09
     stan
    -0.09
    ä¼Ĺ
    -0.08
    lua
    -0.08
     Mario
    -0.08
    unders
    -0.08
    _lua
    -0.08
    POSITIVE LOGITS
    索尼
    0.13
     Xperia
    0.11
    Sony
    0.11
    éĶIJ
    0.11
     Sony
    0.10
    èĬľæ¹ĸ
    0.10
    àªĨ
    0.10
    rette
    0.09
     Mats
    0.09
    磶
    0.09
    Activations Density 0.055%

    No Known Activations