© 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. 11992
    Prev
    Next
    INDEX
    Explanations

    anniversary events or editions

    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
    ä¸ĵå¿ĥ
    -0.21
     Nunes
    -0.19
    é»ijå¤ľ
    -0.19
    第ä¸Ģ天
    -0.19
    æĹĥ
    -0.19
     pond
    -0.19
    sdk
    -0.18
    èľķ
    -0.18
    _kw
    -0.18
    æŁ¥çľĭ详æĥħ
    -0.18
    POSITIVE LOGITS
    åİĨåı²æĸ°
    0.20
    å¹´çĶ±
    0.19
    è·
    0.19
    è¿ĽåŁİ
    0.19
    åĬ¬
    0.19
    ä¹ĭéĻħ
    0.18
    orical
    0.18
    usal
    0.18
    å·²ä¹ħ
    0.18
    èIJ½åľ°
    0.17
    Activations Density 0.010%

    No Known Activations