© 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. 62841
    Prev
    Next
    INDEX
    Explanations

    following "post"

    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
    å¾ģæĪĺ
    -0.10
    éģ¿å¼Ģ
    -0.10
    è¿ľæĸ¹
    -0.09
    çĬĦ
    -0.09
    æīĵæĸŃ
    -0.09
    涨
    -0.09
    æ§İ
    -0.09
    .CONTENT
    -0.09
    è¿Ļæł·è¯´
    -0.09
    å¹´åīį
    -0.09
    POSITIVE LOGITS
     post
    0.16
     Post
    0.14
    Post
    0.13
    (post
    0.12
    _post
    0.12
    post
    0.12
    .post
    0.12
     aftermath
    0.12
    æĶ¶æĭ¾
    0.12
    èµĽåIJİ
    0.12
    Activations Density 0.311%

    No Known Activations