© 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. 4079
    Prev
    Next
    INDEX
    Explanations

    accessible or reachable

    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
    èĩªæķij
    -0.09
    带åĽŀ
    -0.09
    空æ°Ķä¸Ń
    -0.09
    åIJĦ个çݯèĬĤ
    -0.08
     verg
    -0.08
    ult
    -0.08
    åĨįéĢł
    -0.08
    è¡«
    -0.08
    è¡Įä¸ļåįıä¼ļ
    -0.08
    æ³ī
    -0.08
    POSITIVE LOGITS
     accessibility
    0.14
     ìłijê·¼
    0.13
    reachable
    0.13
    åı¯éĢļè¿ĩ
    0.13
     reachable
    0.13
    访éĹ®
    0.12
    åı¯è¾¾
    0.12
     Accessibility
    0.12
    ãĤ¢ãĤ¯ãĤ»ãĤ¹
    0.12
     Reached
    0.12
    Activations Density 0.131%

    No Known Activations