© 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. 47911
    Prev
    Next
    INDEX
    Explanations

    not followed by various words

    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
    ologically
    -0.09
    iana
    -0.09
    urar
    -0.09
    ä¼ı
    -0.08
    inous
    -0.08
    astr
    -0.08
    ç¬ijäºĨ
    -0.08
    ushort
    -0.08
    åŀĤ
    -0.08
    ungi
    -0.08
    POSITIVE LOGITS
    igate
    0.10
    earn
    0.10
    ä½ĨçĶ±äºİ
    0.09
    æĺİãĤī
    0.09
    举æĸ¹
    0.09
    éĶ¦æłĩ
    0.08
    terra
    0.08
    pid
    0.08
    ä¸ĢåĽŀäºĭ
    0.08
    åħ¨æ°ijåģ¥èº«
    0.08
    Activations Density 0.016%

    No Known Activations