© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 33322
    Prev
    Next
    INDEX
    Explanations

    or the like

    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
    åŀĤ
    -0.10
    è¿Ļä½į
    -0.10
    俾
    -0.10
    èĤĺ
    -0.09
    åĬłæĮģ
    -0.09
    ä¸ĭæ²ī
    -0.09
    åı£å¾Ħ
    -0.09
    èħĪ
    -0.09
    尺度
    -0.09
    æĿŁ
    -0.08
    POSITIVE LOGITS
    ä»»ä½ķå½¢å¼ı
    0.10
    常è§ģçļĦ
    0.09
    å®ħ
    0.09
    类似
    0.09
    ographies
    0.09
    åĩ¡æĺ¯
    0.09
    åıªè¦ģæĺ¯
    0.09
    è¦ģç´§
    0.08
    çħ§æł·
    0.08
    è¿Ļç±»
    0.08
    Activations Density 0.381%

    No Known Activations