© 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. 39859
    Prev
    Next
    INDEX
    Explanations

    tunnel, railway, construction

    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
    åį«æĺŁ
    -0.10
    ä¸Ģåī¯
    -0.10
    纰
    -0.09
    èŀŁ
    -0.09
    俯
    -0.09
    ngr
    -0.09
    对å¾ħ
    -0.09
    èĥĢ
    -0.09
    ä¸ĭ乡
    -0.09
     bubble
    -0.09
    POSITIVE LOGITS
    åĵģä½į
    0.10
    åľ°ä¸ĭæ°´
    0.10
     Vault
    0.10
    ç¡IJ
    0.09
    æİ¢éĻ©
    0.09
    湿度
    0.09
    åİħ
    0.09
     flashlight
    0.09
    大åİħ
    0.09
    åľ¨éĩĮéĿ¢
    0.09
    Activations Density 0.067%

    No Known Activations