© 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. 11832
    Prev
    Next
    INDEX
    Explanations

    phone and communication devices

    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
     è¾ĵ
    -0.23
    eil
    -0.22
    èĭĹ
    -0.21
    æŃ£å®Ĺ
    -0.21
    èĬ½
    -0.20
    éķľå¤´
    -0.19
    æľŁæľĽ
    -0.19
    zion
    -0.19
    年人
    -0.19
    é¦ĸ款
    -0.18
    POSITIVE LOGITS
     давно
    0.22
    azzi
    0.21
     cust
    0.21
    æĿ¥ä¸įåıĬ
    0.20
    itter
    0.20
     seized
    0.19
    cust
    0.19
    olley
    0.19
    è¿ĻäºĽä¸ľè¥¿
    0.19
    jie
    0.19
    Activations Density 0.022%

    No Known Activations