© 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. 14785
    Prev
    Next
    INDEX
    Explanations

    block, remove, prevent, repeal

    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
     меÑħ
    -0.19
    ãĤ¹ãĥĿãĥĥãĥĪ
    -0.19
    gly
    -0.19
    LEC
    -0.18
    hem
    -0.18
    è°ģéĥ½
    -0.18
    ensch
    -0.18
    linger
    -0.18
    arter
    -0.17
    è§Ģ
    -0.17
    POSITIVE LOGITS
     Hud
    0.19
    uous
    0.18
     lap
    0.18
    çŃīæĥħåĨµ
    0.18
     Bew
    0.17
    æĻ¡
    0.17
    alled
    0.17
    åĬ£
    0.17
    å½ĵä¹ĭ
    0.17
    éĹªçĥģ
    0.17
    Activations Density 0.096%

    No Known Activations