© 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. 37723
    Prev
    Next
    INDEX
    Explanations

    bone fracture risk

    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
    åĭĥåĭĥ
    -0.10
    ensions
    -0.10
    åĪ©äºİ
    -0.09
     prospect
    -0.09
    æľį饰
    -0.09
    nis
    -0.09
    ote
    -0.08
    aji
    -0.08
    ihil
    -0.08
    rite
    -0.08
    POSITIVE LOGITS
    累累
    0.12
    edList
    0.10
    atos
    0.10
    çĹķ
    0.10
    lew
    0.09
    ree
    0.09
    аÑİÑĤÑģÑı
    0.09
    ober
    0.09
    ively
    0.09
    urent
    0.09
    Activations Density 0.023%

    No Known Activations