© 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. 1752
    Prev
    Next
    INDEX
    Explanations

    biological significance

    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
    åıĹåĪ°
    -0.10
    缴éĶĢ
    -0.10
    åıĹåĪ°äºĨ
    -0.10
    kdir
    -0.09
    åħ¼
    -0.09
    åºŁæŧ
    -0.09
    åıĸå¾Ĺ以åıĬ
    -0.09
    æ·±åıĹ
    -0.09
    $core
    -0.09
     blas
    -0.09
    POSITIVE LOGITS
    ä¼ļå½±åĵį
    0.20
    å½±åĵį
    0.18
    ä¼ļå½±åĵįåĪ°
    0.16
    严éĩįå½±åĵį
    0.14
    å½±éŁ¿
    0.14
    åı¯èĥ½å¯¼èĩ´
    0.13
     влиÑı
    0.13
    åĽłç´ł
    0.12
    çļĦå½±åĵį
    0.12
    导èĩ´
    0.12
    Activations Density 0.255%

    No Known Activations