© 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. 14581
    Prev
    Next
    INDEX
    Explanations

    feeling something

    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
    elman
    -0.20
    коÑģ
    -0.20
    åıijè¾¾
    -0.20
    é¢ľåĢ¼
    -0.19
    ä¾¿å®ľ
    -0.19
    pone
    -0.18
     Opcode
    -0.18
    åŃ
    -0.18
    çĽ¸ä¿¡å¤§å®¶
    -0.18
    POSE
    -0.18
    POSITIVE LOGITS
    oha
    0.21
    Feels
    0.19
    ollo
    0.19
    ä¸ĢåĪĢ
    0.19
    ogl
    0.19
     earned
    0.18
    éĢĥ
    0.18
    /h
    0.18
     sensation
    0.18
    ä¸įåĪ°
    0.18
    Activations Density 0.010%

    No Known Activations