© 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. 7186
    Prev
    Next
    INDEX
    Explanations

    storage spaces

    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
    ance
    -0.09
    ArrayOf
    -0.09
    TING
    -0.09
     вÑĢемен
    -0.09
    Č
    -0.09
    ilia
    -0.08
    ificates
    -0.08
    沸
    -0.08
    rema
    -0.08
    sc
    -0.08
    POSITIVE LOGITS
    æĸ°ä¸ī
    0.10
    çĤ¸å¼¹
    0.09
    é¹°
    0.09
    å°ıå¿ĥ
    0.09
    åĩºå±Ģ
    0.09
    automation
    0.09
    èļĤ
    0.08
    å¸ı
    0.08
    horse
    0.08
    ep
    0.08
    Activations Density 0.003%

    No Known Activations