© 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. 55920
    Prev
    Next
    INDEX
    Explanations

    places and establishments

    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
    è¿Ń
    -0.09
    amba
    -0.09
    bread
    -0.08
    çĥĬ
    -0.08
    åıł
    -0.08
    æĪijéĥ½
    -0.08
    ROY
    -0.08
    azzi
    -0.08
    å¤±æľĽ
    -0.08
    ëŀĺ
    -0.08
    POSITIVE LOGITS
    å¸ļ
    0.10
    佩
    0.10
    è¾ĩ
    0.09
    pedia
    0.09
    å¤ļä½Ļ
    0.09
    itar
    0.09
    ä¸Ģç«Ļ
    0.09
    æ°¸ä¹ħ
    0.08
    Entity
    0.08
    _almost
    0.08
    Activations Density 0.038%

    No Known Activations