© 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. 11896
    Prev
    Next
    INDEX
    Explanations

    opening / opened

    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
    /object
    -0.18
    à¹Į
    -0.16
    ocracy
    -0.16
    iming
    -0.15
    sut
    -0.15
    lice
    -0.15
    allback
    -0.15
    åĩºåľº
    -0.15
    å·¥ä½ľèĢħ
    -0.15
    istic
    -0.15
    POSITIVE LOGITS
    -ended
    0.25
    éĺħ读åħ¨æĸĩ
    0.22
    à¹Ģà¸ľà¸¢
    0.20
    /close
    0.20
    weathermap
    0.19
    ä¸İåıijå±ķ
    0.19
    çľ¼çķĮ
    0.18
    äºĨä¸Ģ
    0.18
    åĴĮåıijå±ķ
    0.18
    æīī
    0.18
    Activations Density 0.094%

    No Known Activations