© 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. 14199
    Prev
    Next
    INDEX
    Explanations

    media company or publication

    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
    s
    -0.23
    inee
    -0.20
     urn
    -0.18
    æķijåij½
    -0.18
    ing
    -0.18
    rypt
    -0.18
    常
    -0.18
     pob
    -0.18
    .SYSTEM
    -0.17
    rend
    -0.17
    POSITIVE LOGITS
    æĹĹä¸ĭçļĦ
    0.20
     fkk
    0.20
    æĹĹä¸ĭ
    0.20
    ÅŁt
    0.20
    rides
    0.19
    ture
    0.19
    cycle
    0.18
    arms
    0.18
    terra
    0.18
    weekly
    0.18
    Activations Density 0.005%

    No Known Activations