© 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. 5885
    Prev
    Next
    INDEX
    Explanations

    Cape of Good Hope

    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
     mort
    -0.09
    èī®
    -0.09
    park
    -0.09
    TTY
    -0.08
    åĩ°
    -0.08
    çĶ¨å¿ĥ
    -0.08
    SAMPLE
    -0.08
     Fla
    -0.08
    StateException
    -0.08
    羣è¯ļ
    -0.08
    POSITIVE LOGITS
    津贴
    0.09
    ç°¿
    0.09
    çĬį
    0.08
    gable
    0.08
     appe
    0.08
    åŁºæķ°
    0.08
    esta
    0.08
     tuner
    0.08
     MX
    0.08
    åīĤ
    0.08
    Activations Density 0.189%

    No Known Activations