© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52366
    Prev
    Next
    INDEX
    Explanations

    Ghana

    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
    æľ«
    -0.10
    å°ī
    -0.09
    æĤīå°¼
    -0.09
    éħį
    -0.09
    岫
    -0.09
    abal
    -0.09
    翼
    -0.09
    æĤ¯
    -0.08
    abbit
    -0.08
    å®ķ
    -0.08
    POSITIVE LOGITS
     Ghana
    0.15
    éĤ¦
    0.10
    ueling
    0.09
    éĩijåĪļ
    0.09
     tre
    0.09
     Guns
    0.09
    èļ
    0.09
    è½½
    0.09
    æ²³åįĹ
    0.08
     bul
    0.08
    Activations Density 0.087%

    No Known Activations