© 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. 16442
    Prev
    Next
    INDEX
    Explanations

    map

    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
    SupportedContent
    -0.27
    InitStruct
    -0.23
     raÄŁ
    -0.23
    .Op
    -0.23
    numerusform
    -0.23
    #aa
    -0.22
    PropertyParams
    -0.22
     spep
    -0.22
    SplitOptions
    -0.21
     saģlıkl
    -0.21
    POSITIVE LOGITS
    åľ°åĽ¾
    0.51
    åľ°å½¢
    0.47
    çļĦåľ°åĽ¾
    0.44
     map
    0.40
    åľ°çIJĨ
    0.39
     maps
    0.35
    æµĭç»ĺ
    0.34
    åľ°è²Į
    0.33
    ç»ĺåĪ¶
    0.33
    (map
    0.32
    Activations Density 0.111%

    No Known Activations