© 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. 15955
    Prev
    Next
    INDEX
    Explanations

    Milton Freewater singles

    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
    BP
    -0.22
    house
    -0.22
    FF
    -0.21
     surprisingly
    -0.21
    å°ijéĩı
    -0.20
    FFF
    -0.20
    WP
    -0.20
    Att
    -0.19
     counter
    -0.19
    House
    -0.19
    POSITIVE LOGITS
    ãĥĵãĤ¸ãĥį
    0.23
    há»ķ
    0.22
     strapon
    0.22
    ãģĦãĤīãģ£
    0.21
    ãģĬãģĻãģĻ
    0.21
    uest
    0.21
    dÅĤug
    0.21
    ãģ¨ãģ«ãģĭ
    0.21
    ãĥijãĥijæ´»
    0.21
    éĽ»è©±åıĬ
    0.21
    Activations Density 0.026%

    No Known Activations