© 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. 13778
    Prev
    Next
    INDEX
    Explanations

    Attorney general

    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
    -0.26
    ëģĶ
    -0.23
    tures
    -0.22
    æł·çļĦ
    -0.18
    TURE
    -0.18
    åĦ¿
    -0.18
    ingly
    -0.18
    ../../../
    -0.17
    ½
    -0.17
    -ever
    -0.17
    POSITIVE LOGITS
    ties
    0.24
    resses
    0.20
    .TryParse
    0.19
    ities
    0.19
    éĻIJãĤĬ
    0.17
    istic
    0.17
    çŀŃ
    0.16
    ched
    0.16
    rees
    0.16
    ship
    0.16
    Activations Density 0.029%

    No Known Activations