© 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. 62403
    Prev
    Next
    INDEX
    Explanations

    facebook

    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
    èŀįåªĴä½ĵ
    -0.09
    ocity
    -0.09
    æĹĮ
    -0.09
    Unused
    -0.09
    imid
    -0.09
     guts
    -0.08
    æĸ°åĬ¨èĥ½
    -0.08
    æ²»çIJĨä½ĵç³»
    -0.08
    åıij声
    -0.08
    Md
    -0.08
    POSITIVE LOGITS
     Facebook
    0.11
    Facebook
    0.11
     facebook
    0.11
    .facebook
    0.10
    facebook
    0.10
    /facebook
    0.10
    åĭ¾
    0.09
    xfb
    0.09
    ä½ıéĻ¢
    0.09
    รว
    0.09
    Activations Density 0.203%

    No Known Activations