© 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. 52348
    Prev
    Next
    INDEX
    Explanations

    fibula or fibroma

    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
    aping
    -0.10
    oran
    -0.09
    ora
    -0.09
    è¹
    -0.09
    ji
    -0.08
     Stranger
    -0.08
    fov
    -0.08
    acting
    -0.08
     SLOT
    -0.08
    apes
    -0.08
    POSITIVE LOGITS
    rous
    0.12
    é³Ĺ
    0.11
    ULAR
    0.11
    laÅŁ
    0.10
    Trap
    0.10
    å¸ĥæĭī
    0.09
    илоÑģÑĮ
    0.09
    eam
    0.09
    rosis
    0.09
    ç´Ĭ
    0.09
    Activations Density 0.057%

    No Known Activations