© 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. 31933
    Prev
    Next
    INDEX
    Explanations

    routes, paths, pathways, or avenues

    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
    姿åĬ¿
    -0.09
    berger
    -0.09
    Ñıд
    -0.08
    è¶´åľ¨
    -0.08
    apiro
    -0.08
    趴
    -0.08
     пÑĢоÑĤиво
    -0.08
    afx
    -0.08
    åĪ·æĸ°
    -0.08
    åħľ
    -0.08
    POSITIVE LOGITS
    éĢĶå¾Ħ
    0.24
    è·¯å¾Ħ
    0.21
    è¿ĻæĿ¡è·¯
    0.20
     paths
    0.19
     Paths
    0.17
    ä¹ĭè·¯
    0.17
     pathways
    0.17
     path
    0.17
    éĢĶ
    0.17
     route
    0.16
    Activations Density 0.115%

    No Known Activations