© 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
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 5451
    Prev
    Next
    INDEX
    Explanations

    verb ending in ing

    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
    ëį°
    -0.24
    ings
    -0.22
    ÂŃing
    -0.17
    ingly
    -0.15
    /remove
    -0.15
    INGS
    -0.14
    able
    -0.14
    ers
    -0.14
    инг
    -0.14
    /disable
    -0.13
    POSITIVE LOGITS
    redients
    0.16
    redient
    0.15
    ly
    0.13
    /testing
    0.13
    enuity
    0.12
    /loading
    0.12
    /up
    0.12
    /rem
    0.12
     oneself
    0.11
    æīĵæī®
    0.10
    Activations Density 2.121%

    No Known Activations