© 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. 13209
    Prev
    Next
    INDEX
    Explanations

    Bell followed by customers, TV, ard, or ings

    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
    eel
    -0.17
    ÑģÑı
    -0.16
    eos
    -0.16
    nee
    -0.16
    sic
    -0.16
    ·
    -0.16
    sel
    -0.16
    eur
    -0.15
    ¤
    -0.15
    sWith
    -0.15
    POSITIVE LOGITS
    åŃIJéĩĮ
    0.20
    ows
    0.20
    çıij
    0.19
    éĵĽ
    0.19
     Ñģобой
    0.18
     lẽ
    0.18
    auce
    0.17
    owed
    0.17
    æŁ©
    0.16
    stones
    0.15
    Activations Density 0.016%

    No Known Activations