© 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. 21489
    Prev
    Next
    INDEX
    Explanations

    pinot noir, ale, wine

    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
    eding
    -0.08
    çħİ
    -0.08
    atform
    -0.08
    èĪ¶
    -0.08
     Lambert
    -0.08
    æĸ°æĹ¶æľŁ
    -0.08
    åį´åıijçİ°
    -0.08
    gree
    -0.08
    æ´Ĺ澡
    -0.08
    pan
    -0.08
    POSITIVE LOGITS
    èIJ¸
    0.09
    yro
    0.09
    泡沫
    0.08
    .removeFrom
    0.08
     nam
    0.08
    æŀľ
    0.08
     dripping
    0.08
    HexString
    0.08
    .Transport
    0.08
     CreateMap
    0.08
    Activations Density 0.003%

    No Known Activations