© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37256
    Prev
    Next
    INDEX
    Explanations

    literacy rate

    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
    å¹ħ度
    -0.11
    tl
    -0.09
    ç§ijæĬĢ大åѦ
    -0.08
     besten
    -0.08
    raise
    -0.08
    ritten
    -0.08
    å¾Īæĺ¯
    -0.08
    toolbox
    -0.08
    nil
    -0.07
    å±ģ
    -0.07
    POSITIVE LOGITS
    ä¾Ī
    0.11
    å¤ł
    0.11
    okit
    0.09
    çĤ¹äºĨ
    0.09
    quake
    0.09
    çİĩ为
    0.09
     Äijáo
    0.09
    ÑĤÑĮ
    0.09
    мÑı
    0.09
    éĿĻéĿĻåľ°
    0.08
    Activations Density 0.009%

    No Known Activations