© 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. 15844
    Prev
    Next
    INDEX
    Explanations

    film, fiction, manga, production

    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
    ussen
    -0.20
    alic
    -0.19
     Blowjob
    -0.19
     án
    -0.19
    ROID
    -0.19
    uggy
    -0.19
    reo
    -0.19
    æĻ¤
    -0.18
    uary
    -0.18
    çĭŀ
    -0.18
    POSITIVE LOGITS
     fictional
    0.22
    åī§ä¸Ń
    0.22
     movie
    0.21
     filme
    0.20
     film
    0.20
    åĨ»
    0.20
    å°ı说
    0.20
    ãĢĬ
    0.20
     movies
    0.20
    åī§ç»Ħ
    0.20
    Activations Density 0.104%

    No Known Activations