© 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. 14844
    Prev
    Next
    INDEX
    Explanations

    tie, knot, folded, assignment

    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
     mount
    -0.20
    vens
    -0.19
     Rider
    -0.19
    ogue
    -0.19
    uning
    -0.19
    uity
    -0.18
    è²Ĥ
    -0.18
    ingly
    -0.18
    agner
    -0.18
    pell
    -0.18
    POSITIVE LOGITS
    çĨŁç»ĥ
    0.26
    æĬĢå·§
    0.23
    æĬĢèĥ½
    0.23
    _fold
    0.22
    姿åĬ¿
    0.21
    é«ĺæīĭ
    0.21
     skills
    0.20
     incorrectly
    0.20
     Ñĥме
    0.19
    æĬĬæīĭ
    0.19
    Activations Density 0.010%

    No Known Activations