© 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. 8095
    Prev
    Next
    INDEX
    Explanations

    names starting with jess

    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
    ish
    -0.12
    ãģ¹ãģį
    -0.11
    Å¡t
    -0.10
    ROLLER
    -0.09
    ished
    -0.09
    æĥ³æĥ³
    -0.09
    леÑĤ
    -0.09
    edo
    -0.08
    ers
    -0.08
    scriber
    -0.08
    POSITIVE LOGITS
    ниÑĨа
    0.10
    ignment
    0.10
    æİĪæĿĥ
    0.10
    mania
    0.10
    ×ķף
    0.09
    躬
    0.09
    chen
    0.09
    hone
    0.09
    cribed
    0.09
    ấy
    0.09
    Activations Density 0.018%

    No Known Activations