© 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. 12004
    Prev
    Next
    INDEX
    Explanations

    explicit sexual content

    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
     just
    -0.28
    GenerationStrategy
    -0.26
    (Initialized
    -0.26
     right
    -0.25
     )↵↵↵↵↵↵↵↵
    -0.24
    <LM
    -0.24
     big
    -0.23
    à¸Ńำà¸Ļวยà¸Ħวาม
    -0.22
     tr
    -0.22
    EmptyEntries
    -0.22
    POSITIVE LOGITS
    åĽłæѤ
    0.29
     handjob
    0.28
    è¿Ļæĺ¯åĽłä¸º
    0.27
     gangbang
    0.27
    ä½ĨçĶ±äºİ
    0.26
    swire
    0.25
    ä¾ĭå¦Ĥ
    0.25
    åĽłèĢĮ
    0.25
    ä¹Łå°±æĺ¯è¯´
    0.25
    åį³
    0.25
    Activations Density 0.651%

    No Known Activations