© 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. 12888
    Prev
    Next
    INDEX
    Explanations

    Superman and related characters

    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
    umen
    -0.20
    oba
    -0.19
    è¹¼
    -0.17
    èĻİ
    -0.17
    Modern
    -0.17
     UNC
    -0.16
    loh
    -0.16
     Bon
    -0.16
    ument
    -0.16
    hips
    -0.16
    POSITIVE LOGITS
    åĽ½éĻħæľºåľº
    0.19
    å¨ĥå¨ĥ
    0.18
    çİ»çĴĥ
    0.18
    inic
    0.18
    adin
    0.18
     glasses
    0.18
    ä¾Ľç»Ļ侧
    0.18
     Gujar
    0.17
    çĵĴ
    0.17
    blr
    0.17
    Activations Density 0.004%

    No Known Activations