© 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. 16141
    Prev
    Next
    INDEX
    Explanations

    hall of fame

    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
    ted
    -0.21
    ยว
    -0.17
    ially
    -0.16
    çĽİ
    -0.16
    ä¸İåıijå±ķ
    -0.16
    顽强
    -0.16
    çİĩè¾¾
    -0.16
    ationally
    -0.16
    hte
    -0.16
    ä¹IJåĽŃ
    -0.16
    POSITIVE LOGITS
    ways
    0.26
    ows
    0.25
    mates
    0.24
    iday
    0.24
    marks
    0.23
    keepers
    0.20
    esian
    0.19
    vard
    0.19
    room
    0.19
    åĵ¡
    0.18
    Activations Density 0.013%

    No Known Activations