© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7922
    Prev
    Next
    INDEX
    Explanations

    northwestern and southwestern areas

    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
     Ñģобой
    -0.13
     ë¶Ī구íķĺê³ł
    -0.10
    chaft
    -0.09
    èĬŁ
    -0.09
    ruise
    -0.09
    illos
    -0.09
    éĻĮ
    -0.09
    ensus
    -0.09
    olver
    -0.09
    okino
    -0.08
    POSITIVE LOGITS
    er
    0.12
    ings
    0.11
    spl
    0.10
    thal
    0.10
    ãģ¾ãģĻãģĮ
    0.10
    ly
    0.09
    eri
    0.09
    ness
    0.09
    庸
    0.09
    aires
    0.09
    Activations Density 0.008%

    No Known Activations