© 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. 12178
    Prev
    Next
    INDEX
    Explanations

    DIY projects

    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
    ourses
    -0.16
    _PRI
    -0.16
     privileged
    -0.16
    ISS
    -0.15
    PRI
    -0.15
     privé
    -0.15
    èĤī
    -0.15
    ä»
    -0.15
    èį¯å¸Ī
    -0.15
    æŃ¢ãĤģ
    -0.15
    POSITIVE LOGITS
    ers
    0.23
    ðŁı»
    0.21
    çĪ±å¥½èĢħ
    0.20
    ï¸
    0.19
    kit
    0.18
    èĢħ
    0.18
    æĭĻ
    0.18
    ðŁı¼
    0.17
    ode
    0.17
    ä¹ĭè·¯
    0.17
    Activations Density 0.004%

    No Known Activations