© 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. 13182
    Prev
    Next
    INDEX
    Explanations

    acoustic 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
    æĪ¾
    -0.21
    å®ł
    -0.19
    çĦ¯
    -0.19
    åļı
    -0.19
    è¹Ī
    -0.18
    é¾Ħ
    -0.18
    éĽī
    -0.18
    沤
    -0.17
     Evel
    -0.17
    egot
    -0.17
    POSITIVE LOGITS
     version
    0.20
    friendly
    0.20
    -type
    0.20
    versions
    0.19
     versions
    0.19
    æĥħåĨµä¸ĭ
    0.19
    éĩįåŀĭ
    0.18
    çīĪ
    0.18
    éĥ¨éĥ¨éķ¿
    0.18
    addElement
    0.18
    Activations Density 0.005%

    No Known Activations