© 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
    2. Qwen3-14B
    3. 20-RESID-BATCHTOPK-65K__L0-80
    4. 11073
    Prev
    Next
    INDEX
    Explanations

    academic writing: thesis, dissertation, essay

    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
    ownership
    -0.19
    å¹¶ä¸į代表
    -0.19
    fiction
    -0.19
    éĺ¡
    -0.18
    ç»Ħéķ¿
    -0.18
    afi
    -0.18
    åijĺ
    -0.18
    geist
    -0.18
    _Query
    -0.17
    ÙĤاد
    -0.17
    POSITIVE LOGITS
     ÑģÑĤÑĥд
    0.22
    PID
    0.21
    CU
    0.20
    åĽ«
    0.20
    æ¡Ĥ
    0.19
    æ±²
    0.18
    被éªĹ
    0.18
    åIJİå¤ĩ
    0.18
    åį§
    0.18
    æ¯įæł¡
    0.18
    Activations Density 0.004%

    No Known Activations