© 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. 12688
    Prev
    Next
    INDEX
    Explanations

    erotic stories

    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
    ç¯ĩç«ł
    -0.24
    åĭł
    -0.24
    flash
    -0.22
    is
    -0.21
    Extended
    -0.21
    Row
    -0.21
    atur
    -0.21
    ...
    -0.20
    {:
    -0.20
    æĸĩçī©
    -0.20
    POSITIVE LOGITS
     Geile
    0.41
    schlü
    0.39
     Erotische
    0.39
     geschichten
    0.39
    èĮĥåĨ°
    0.38
    europäische
    0.35
    ãĤŃãĥ£ãĥ³ãĥļ
    0.35
    à¹Ĥà¸Ľà¸£à¹ģ
    0.35
     fetisch
    0.33
    ÑĢеги
    0.33
    Activations Density 0.069%

    No Known Activations