© 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. 54023
    Prev
    Next
    INDEX
    Explanations

    date and metadata labels

    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
    使人
    -0.08
    忸
    -0.08
     delt
    -0.08
    éľį
    -0.08
    ESCO
    -0.07
    5
    -0.07
    3
    -0.07
    4
    -0.07
    ä¹Łèĥ½
    -0.07
    å¤ļä¹Ī
    -0.07
    POSITIVE LOGITS
    æłĩçļĦ
    0.09
    à¹Ģà¸Ńà¸ģ
    0.09
    å®Įç¾İçļĦ
    0.09
    ä¼°
    0.08
    ATAR
    0.08
    .vec
    0.08
    æĸ°ä¸ī
    0.08
    yne
    0.08
    妾
    0.08
    è¯ģçĽij
    0.08
    Activations Density 0.492%

    No Known Activations