© 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. 61278
    Prev
    Next
    INDEX
    Explanations

    wondering how or if

    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
    好åIJ§
    -0.10
    äºĨåIJ§
    -0.09
     Tos
    -0.09
    蹩
    -0.09
    åĬłæ²¹
    -0.08
    ç²¾è£ħ
    -0.08
    åı¯ä¸įæĺ¯
    -0.08
    çĭĥ
    -0.08
    dash
    -0.08
    /IP
    -0.08
    POSITIVE LOGITS
    请éĹ®
    0.15
    éĹ®
    0.12
    éĹ®éĹ®
    0.11
    请æķĻ
    0.10
    æľī没æľī
    0.10
    åĪį
    0.09
     wonder
    0.09
    请æĤ¨
    0.09
     wondering
    0.09
    éĹ®ä»ĸ
    0.09
    Activations Density 0.237%

    No Known Activations