© 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. 37937
    Prev
    Next
    INDEX
    Explanations

    Adams and related names

    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
    ered
    -0.12
    ingly
    -0.10
    eros
    -0.10
    ipt
    -0.10
    er
    -0.10
    eren
    -0.09
    å¸
    -0.09
    itud
    -0.09
    ambda
    -0.09
    åĶ§
    -0.08
    POSITIVE LOGITS
    VERTISEMENT
    0.11
    son
    0.10
    cul
    0.10
    mitted
    0.10
    ively
    0.10
    综åIJĪç´łè´¨
    0.09
    é¢ı
    0.09
    resses
    0.09
    azzi
    0.09
    vertis
    0.09
    Activations Density 0.008%

    No Known Activations