© 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. 56253
    Prev
    Next
    INDEX
    Explanations

    interactive technologies

    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
    åľ°ä¸Ń
    -0.09
    浩
    -0.08
    åį°
    -0.08
    fn
    -0.08
    éĵĭ
    -0.08
    æīĪ
    -0.08
    æīĽ
    -0.08
    Printing
    -0.08
     article
    -0.08
    ered
    -0.08
    POSITIVE LOGITS
    åĹ½
    0.10
    åľ¨äº¬
    0.10
    onus
    0.09
    .datab
    0.09
    åĥµå°¸
    0.09
    URAL
    0.09
    æĮĤçīĮ
    0.09
    INGER
    0.09
    对æĸ¹
    0.08
    ë³ij
    0.08
    Activations Density 0.098%

    No Known Activations