© 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. 13441
    Prev
    Next
    INDEX
    Explanations

    management, goal, ability, spread, improving, safe, bandwidth, readability

    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
    è¿ĻäºĽéĹ®é¢ĺ
    -0.22
    _hooks
    -0.19
    .listeners
    -0.19
    ACC
    -0.19
    acios
    -0.18
    -hooks
    -0.18
    nÃŃ
    -0.18
    ÅŁÄ±k
    -0.18
    éĵ®
    -0.18
    rå
    -0.18
    POSITIVE LOGITS
    æĹ©æĹ¥
    0.19
    j
    0.19
    åıijæī¬
    0.19
    ly
    0.18
    Sp
    0.18
    uber
    0.18
    still
    0.18
    åĨ³æĪĺ
    0.18
    æľīæĽ´å¤ļçļĦ
    0.18
    ney
    0.18
    Activations Density 0.425%

    No Known Activations