© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 32277
    Prev
    Next
    INDEX
    Explanations

    scalable and scalability

    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
    äºĨä¸Ģéģį
    -0.09
    å®Į好
    -0.08
    erson
    -0.08
    ired
    -0.08
    <IEnumerable
    -0.08
    TEGR
    -0.08
    FML
    -0.08
    iso
    -0.08
    appings
    -0.08
    acad
    -0.08
    POSITIVE LOGITS
    æĪIJéķ·
    0.11
    æĪIJéķ¿
    0.10
    grow
    0.10
    èĭ´
    0.10
    è¦ı模
    0.09
    å°ĨæĿ¥
    0.09
    æī©å±ķ
    0.09
    /rest
    0.09
    容纳
    0.09
    scal
    0.09
    Activations Density 0.043%

    No Known Activations