© 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. 11901
    Prev
    Next
    INDEX
    Explanations

    components and parts

    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
    ä¸İåıijå±ķ
    -0.24
    äºĨä¸Ģä¸ĭ
    -0.20
    æĢİä¹Ī说
    -0.19
    çĹħæ¯ĴæĦŁæŁĵ
    -0.19
    ç½ij游
    -0.18
    æłİ
    -0.18
    åĽ°æĥij
    -0.18
     fkk
    -0.17
    _READONLY
    -0.17
    connections
    -0.17
    POSITIVE LOGITS
    ç±»åŀĭ
    0.28
    æĢ§èĥ½
    0.27
    æľ¬èº«çļĦ
    0.26
     types
    0.25
    åıĬåħ¶
    0.23
    à¹Ģà¸Ĺà¸Ħà¹Ĥà¸Ļ
    0.23
    端
    0.23
    æľ¬èº«
    0.23
     type
    0.22
     parameters
    0.22
    Activations Density 0.722%

    No Known Activations