© 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. 27280
    Prev
    Next
    INDEX
    Explanations

    conversion and change

    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
    ä¸įä¼ļåĨį
    -0.09
    HIP
    -0.09
    æĶ¾åĩº
    -0.08
    rez
    -0.08
    ç®Ń
    -0.08
    ograf
    -0.08
    社ä¼ļæķĪçĽĬ
    -0.08
    èµĻ
    -0.08
    æħĭ
    -0.08
    AccessException
    -0.08
    POSITIVE LOGITS
    è¦ģ害
    0.11
    çİĩè¾¾
    0.10
    为空
    0.10
    åĩłåı¥
    0.09
    å¿ĥä¸ŃçļĦ
    0.09
    çİĩè¾¾åĪ°
    0.08
    ılan
    0.08
    ERO
    0.08
    æijĦå½±å¸Ī
    0.08
    ä¸įäºĨ
    0.08
    Activations Density 0.010%

    No Known Activations