© 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. 33402
    Prev
    Next
    INDEX
    Explanations

    chestnut and Chesapeake

    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
    éŁŃ
    -0.09
    失åİ»äºĨ
    -0.08
    age
    -0.08
    æĻº
    -0.08
    éĺ¡
    -0.08
    ืà¸Ļ
    -0.08
    6
    -0.08
    asti
    -0.08
    ture
    -0.08
    æĵİ
    -0.08
    POSITIVE LOGITS
    æł¹æį®èĩªå·±
    0.10
    åĭĥåĭĥ
    0.10
    apeake
    0.10
    çĽ¥
    0.09
    nut
    0.09
    wig
    0.09
     Bucc
    0.09
    nuts
    0.09
    ertime
    0.09
    ãģ£ãģįãĤĬ
    0.09
    Activations Density 0.007%

    No Known Activations