© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21375
    Prev
    Next
    INDEX
    Explanations

    a + [problem/injury]

    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
    launch
    -0.09
    è°±
    -0.09
     fit
    -0.08
    å¾Ģä¸Ĭ
    -0.08
    èı±
    -0.08
    ê·¹
    -0.08
    为åħ¶
    -0.08
    æĭ³
    -0.08
    ÑĢоз
    -0.08
    çļĦä¸Ģéĥ¨åĪĨ
    -0.08
    POSITIVE LOGITS
    驱
    0.08
    ording
    0.08
    åĪĽ
    0.08
    æķŀ
    0.08
    _DRIVE
    0.08
    çIJĨæĥ³ä¿¡å¿µ
    0.08
    å§Ŀ
    0.08
    æ±°
    0.08
    ural
    0.08
    OTS
    0.08
    Activations Density 0.107%

    No Known Activations