© 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. 11864
    Prev
    Next
    INDEX
    Explanations

    good morning or good friday

    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
    éĴ§
    -0.19
    çĬ¹
    -0.18
    åĢĴ
    -0.18
    çĶļèĩ³æĺ¯
    -0.18
    ä¿ĥ
    -0.17
    éĻIJ度
    -0.17
    angement
    -0.16
    å³Ń
    -0.16
    使ä¹ĭ
    -0.16
    åĪ°
    -0.16
    POSITIVE LOGITS
    _EOF
    0.18
    ë°±
    0.17
    sworth
    0.17
    çĹĺ
    0.17
    tright
    0.17
    еÑģÑĤво
    0.17
    çĪ·
    0.17
    liness
    0.17
    night
    0.16
    stell
    0.16
    Activations Density 0.025%

    No Known Activations