© 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. 14812
    Prev
    Next
    INDEX
    Explanations

    formed shapes

    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
    UME
    -0.22
    berra
    -0.21
    踵
    -0.21
    ForObject
    -0.19
    ume
    -0.19
    getic
    -0.18
     modne
    -0.18
    неÑĨ
    -0.18
    äºĴåĬ©
    -0.18
    gne
    -0.18
    POSITIVE LOGITS
     formed
    0.35
     formations
    0.32
     formation
    0.31
    æĪIJåŀĭ
    0.29
    æĪIJç«ĭ
    0.29
     Formation
    0.29
    å®Įæķ´çļĦ
    0.28
    å½¢æĪIJ
    0.27
    formed
    0.26
    å®Įæķ´
    0.25
    Activations Density 0.184%

    No Known Activations