© 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. 21471
    Prev
    Next
    INDEX
    Explanations

    fear of

    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
    olu
    -0.09
    king
    -0.08
    æ·±åıĹ
    -0.08
    æĦŁåıĹåĪ°äºĨ
    -0.08
    arro
    -0.08
     ÑĤÑĢеб
    -0.08
    潤
    -0.08
    æľĢå¿«çļĦ
    -0.08
    mx
    -0.08
    еÑģп
    -0.08
    POSITIVE LOGITS
    ä»Ģä¹Īåij¢
    0.14
    çķı
    0.12
    æĢķ
    0.11
    åıªæĢķ
    0.10
    å·²ä¹ħ
    0.10
    ä¸ĩä¸Ģ
    0.09
    çªģå¦Ĥåħ¶
    0.09
    ì¡°
    0.09
    HING
    0.09
    ãĤį
    0.09
    Activations Density 0.022%

    No Known Activations