© 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. 14820
    Prev
    Next
    INDEX
    Explanations

    photo for selfies

    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
    vell
    -0.24
    æ·Į
    -0.23
    éĨ®
    -0.21
    Sounds
    -0.21
    isko
    -0.20
    moth
    -0.20
    åij·
    -0.19
    affer
    -0.19
     manh
    -0.19
    [temp
    -0.19
    POSITIVE LOGITS
    åIJĪãĤıãģĽ
    0.23
    åIJĪå½±
    0.21
    åĴĮæľįåĬ¡
    0.21
    çķ¶åľ°
    0.19
    taken
    0.19
    pose
    0.19
    æĴ®
    0.19
    uploaded
    0.19
    abs
    0.18
    æłı
    0.18
    Activations Density 0.022%

    No Known Activations