© 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. 62060
    Prev
    Next
    INDEX
    Explanations

    comparative endings (-er, -ier) with "than"

    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
    sWith
    -0.20
    eur
    -0.14
    ers
    -0.13
    fulness
    -0.13
    ert
    -0.11
    y
    -0.11
    sv
    -0.11
    erness
    -0.11
    erson
    -0.11
    äºĨä¸Ģ个
    -0.10
    POSITIVE LOGITS
    -than
    0.25
     вÑģего
    0.14
    çļ¿
    0.14
    than
    0.13
    _than
    0.13
    anging
    0.12
    ocket
    0.12
    _THAN
    0.11
    è¶Ł
    0.11
    adius
    0.10
    Activations Density 0.148%

    No Known Activations