© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9028
    Prev
    Next
    INDEX
    Explanations

    line-of-sight

    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
    æŃ¥æŃ¥
    -0.09
    æİ¢éĻ©
    -0.09
    .nom
    -0.09
    循
    -0.09
    auer
    -0.08
    è¿ĽæĿ¥
    -0.08
    ĽĦ
    -0.08
    oom
    -0.08
    opot
    -0.08
    ouch
    -0.08
    POSITIVE LOGITS
    è¿ŀ线
    0.13
     line
    0.12
     straight
    0.11
    çŁ¢
    0.11
     lines
    0.11
    line
    0.10
    åĽłæŀľ
    0.10
    çĽ´çº¿
    0.10
    çĽ´è¾¾
    0.10
    .line
    0.09
    Activations Density 0.050%

    No Known Activations