© 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. 10797
    Prev
    Next
    INDEX
    Explanations

    sentence terminators and separators

    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
    SES
    -0.19
     HOL
    -0.18
     PAT
    -0.17
    çļĦä¸ĢäºĽ
    -0.17
    ATTR
    -0.17
    åł±å°İ
    -0.17
    Nice
    -0.17
    PRI
    -0.17
     gent
    -0.16
    .createObject
    -0.16
    POSITIVE LOGITS
    çŃīçŃī
    0.24
    以åıĬ
    0.21
    åľ¨çݩ家ä¸Ń
    0.19
    BOSE
    0.19
    alls
    0.19
    гÑĢани
    0.19
    aiser
    0.19
     etc
    0.19
    	TokenName
    0.19
    ators
    0.18
    Activations Density 0.221%

    No Known Activations