© 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. 10988
    Prev
    Next
    INDEX
    Explanations

    prison and jail concepts

    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
    å§Ķåijĺ
    -0.21
    _asm
    -0.20
    æĻļ
    -0.20
    éĺ²æ°´
    -0.19
    åģļå¾Ĺ
    -0.19
    ç´§å¼ł
    -0.19
    çĸ²
    -0.18
    ç²¾çĽĬæ±Ĥç²¾
    -0.18
    åĬŁåĬĽ
    -0.17
    ноÑģÑĤ
    -0.17
    POSITIVE LOGITS
     walls
    0.24
     prison
    0.23
    å¢ĥ
    0.22
    笼
    0.21
     jail
    0.21
    çĽijçĭ±
    0.20
    èŀºæĹĭ
    0.20
    åĨ°åĨ·
    0.20
     Spiral
    0.20
     Walls
    0.20
    Activations Density 0.046%

    No Known Activations