© 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. 8437
    Prev
    Next
    INDEX
    Explanations

    Justin + surname

    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
    ÑĭÑĪ
    -0.11
    ings
    -0.11
    纡
    -0.10
    esi
    -0.10
    褰
    -0.10
    edException
    -0.09
    èĩªè´Ł
    -0.09
    pping
    -0.09
    pper
    -0.09
    éľģ
    -0.09
    POSITIVE LOGITS
     Bieber
    0.09
    ı
    0.09
    ðŁı½
    0.09
    ories
    0.09
    duk
    0.09
    IONS
    0.09
    æĢģ
    0.09
    land
    0.09
    ðŁı»
    0.09
    andalone
    0.08
    Activations Density 0.003%

    No Known Activations