© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15127
    Prev
    Next
    INDEX
    Explanations

    names and associated last names

    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
    ../../../
    -0.22
    ties
    -0.18
    åĴĮåľ°åĮº
    -0.18
    ities
    -0.17
    说æĺ¯
    -0.16
    Ñıм
    -0.16
     оÑģоб
    -0.16
    Ñıв
    -0.16
    poke
    -0.15
    ions
    -0.15
    POSITIVE LOGITS
    arily
    0.17
    /her
    0.16
    ãģĹãģ¾ãģĨ
    0.15
    sek
    0.14
    æ¤ħ
    0.14
    soever
    0.14
    pone
    0.14
    HEME
    0.14
    strom
    0.14
    ulaire
    0.14
    Activations Density 0.527%

    No Known Activations