© 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. 14752
    Prev
    Next
    INDEX
    Explanations

    roles, responsibilities, marriage, tax

    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
    éĨĴ
    -0.22
    é»ijåIJįåįķ
    -0.22
    é«ĺæ¸ħ
    -0.22
    éĢłæĪIJäºĨ
    -0.21
    å¾Īå¿«
    -0.21
    å±Ģ
    -0.21
    è¿Ŀæ³ķ
    -0.21
    decimal
    -0.20
    åģ·åģ·
    -0.20
    æ®ĭ
    -0.20
    POSITIVE LOGITS
    è´²
    0.24
    ä½ĵè´´
    0.23
    .stdin
    0.21
     lá»ĩ
    0.21
     responsibilities
    0.21
    Æ°á»Ľng
    0.21
    _FUNC
    0.20
    ÄĻż
    0.20
    çĪ±æĬ¤
    0.20
    天çĦ¶
    0.19
    Activations Density 0.011%

    No Known Activations