© 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. 10761
    Prev
    Next
    INDEX
    Explanations

    contact information

    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
    è£Ĥ
    -0.21
    heit
    -0.19
    ÅĤu
    -0.18
    åĪļ
    -0.18
    èIJ¥ä¸ļ
    -0.18
    errs
    -0.18
    社
    -0.18
    饼
    -0.18
    ÙĪÙĤ
    -0.17
    年以æĿ¥
    -0.17
    POSITIVE LOGITS
    è§ļ
    0.20
     embar
    0.20
    寤
    0.20
    croft
    0.19
     Pas
    0.19
    ï¸
    0.19
    Condition
    0.19
    åıijæĺİä¸ĵåĪ©
    0.19
    grav
    0.18
    SENS
    0.18
    Activations Density 0.003%

    No Known Activations