© 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. 15653
    Prev
    Next
    INDEX
    Explanations

    Houston Texas

    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
    sWith
    -0.18
    èĹĵ
    -0.17
    auce
    -0.17
    黳
    -0.16
    ulator
    -0.16
    æ¦ĨæŀĹ
    -0.16
    oit
    -0.16
    æŁ©
    -0.16
    rok
    -0.15
     haunt
    -0.15
    POSITIVE LOGITS
    ized
    0.19
    ization
    0.18
    åħ¼é¡¾
    0.17
    assist
    0.17
    ¯
    0.17
    åĮĸè¿Ľç¨ĭ
    0.16
    ÙĬØ©
    0.16
    ä»Ģä¹ĪåİŁåĽł
    0.16
    å¨ĺ
    0.16
    baugh
    0.16
    Activations Density 0.022%

    No Known Activations