© 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. 11264
    Prev
    Next
    INDEX
    Explanations

    Ontario

    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
    ibility
    -0.21
    ible
    -0.20
    说æĺ¯
    -0.20
    æ¸ł
    -0.18
    GED
    -0.18
    å½ĵåľ°æĶ¿åºľ
    -0.17
    天çĦ¶
    -0.17
    ç»ıå¼Ģ
    -0.17
    vant
    -0.17
    ven
    -0.16
    POSITIVE LOGITS
    åĭĥåĭĥ
    0.17
    å°ıå§ijå¨ĺ
    0.17
    -wide
    0.17
    sWith
    0.16
    ãģĬãģı
    0.15
    oogle
    0.15
    rikes
    0.15
    é«ĺéĢŁåıijå±ķ
    0.15
     диагноÑģÑĤ
    0.15
    ector
    0.15
    Activations Density 0.015%

    No Known Activations