© 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. 49556
    Prev
    Next
    INDEX
    Explanations

    breeds and place 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
    éļIJèĶ½
    -0.10
    rides
    -0.09
     HOT
    -0.09
    iggins
    -0.09
     ASF
    -0.09
     Ride
    -0.09
    bung
    -0.09
    åı¯æĥ³èĢĮçŁ¥
    -0.09
    Hop
    -0.09
    é²±
    -0.09
    POSITIVE LOGITS
    æĮĪ
    0.10
    å°ıåŀĭ
    0.10
     Roose
    0.10
    åŃĻ
    0.10
    oodle
    0.09
    å·¨åŀĭ
    0.09
    鼷
    0.09
    _curr
    0.09
    _LVL
    0.08
    à¸Ĺรà¸ĩ
    0.08
    Activations Density 0.124%

    No Known Activations