© 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. 14502
    Prev
    Next
    INDEX
    Explanations

    excessive

    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
    ê¹IJ
    -0.20
    rose
    -0.19
    تØŃ
    -0.17
    ase
    -0.17
    ished
    -0.17
    iffs
    -0.16
    uche
    -0.16
    usch
    -0.16
    å±ij
    -0.16
    eters
    -0.16
    POSITIVE LOGITS
    ity
    0.21
     amount
    0.20
    ä¸įå¿ħè¦ģçļĦ
    0.19
    磨
    0.19
     amounts
    0.18
    ément
    0.18
    ively
    0.18
    ption
    0.16
    è°Ī论
    0.16
    ities
    0.16
    Activations Density 0.007%

    No Known Activations