© 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. 14601
    Prev
    Next
    INDEX
    Explanations

    handsome person descriptions

    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
    åı¥è¯Ŀ
    -0.18
    flows
    -0.17
    istor
    -0.17
    nic
    -0.17
    èľ·
    -0.17
    ç´ļ
    -0.16
    sWith
    -0.16
    à¸ĩาà¸Ļ
    -0.16
    istic
    -0.16
    æŃ¤åŁºç¡Ģä¸Ĭ
    -0.16
    POSITIVE LOGITS
    eer
    0.18
     Aires
    0.18
    boro
    0.18
    esse
    0.17
    paces
    0.17
    esis
    0.17
    ðŁı»
    0.17
    æ·®åįĹ
    0.17
     larg
    0.17
    mith
    0.17
    Activations Density 0.008%

    No Known Activations