© 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. 2078
    Prev
    Next
    INDEX
    Explanations

    mining stock review

    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
    踵
    -0.09
    ä¸įçĦ¶
    -0.09
    SID
    -0.09
    æĹģ
    -0.09
    tek
    -0.09
    åķĦ
    -0.09
    hu
    -0.09
    åħ¥
    -0.08
    è¿ĺ羣
    -0.08
    iah
    -0.08
    POSITIVE LOGITS
    åĭĺæŁ¥
    0.10
    æĻ®æŁ¥
    0.10
    åĭĺæİ¢
    0.10
    åĬłæĭ¿
    0.10
    åĬłæĭ¿å¤§
    0.09
    çŁ¿å±±
    0.09
    åıĪèĥ½
    0.09
    åĻ¤
    0.08
    骸
    0.08
    éĩĩçŁ¿
    0.08
    Activations Density 0.067%

    No Known Activations