© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12957
    Prev
    Next
    INDEX
    Explanations

    names ending in 'k' or similar sounds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    ราย
    -0.30
    ร
    -0.27
    kick
    -0.24
    ราà¸ĩ
    -0.23
    ระหว
    -0.22
    ราà¸Ħา
    -0.22
    รà¸Ń
    -0.21
    รà¸ĸ
    -0.21
    รา
    -0.19
    รà¸Ńà¸ĩ
    -0.19
    POSITIVE LOGITS
    nowledge
    0.34
    nowled
    0.33
    ษา
    0.29
    tober
    0.28
    ernels
    0.27
    NOWLED
    0.24
    raft
    0.23
    ness
    0.23
    rypton
    0.23
    appa
    0.23
    Activations Density 0.954%

    No Known Activations