© 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. 13376
    Prev
    Next
    INDEX
    Explanations

    floors and flooring

    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
    åģľçķĻåľ¨
    -0.20
    _FMT
    -0.20
    çļĦ缮åħī
    -0.19
     trÆ°á»Łng
    -0.19
    etus
    -0.18
    ç»ĨåĮĸ
    -0.18
    亲
    -0.18
    okit
    -0.18
     release
    -0.18
    çģ«çĦ°
    -0.18
    POSITIVE LOGITS
    -floor
    0.21
    åĪĨä¼ļ
    0.21
    newInstance
    0.18
    ä¸īå±Ĥ
    0.18
    FXML
    0.18
    ctr
    0.18
    -mounted
    0.18
    eer
    0.18
    SENSOR
    0.18
    ãģ©ãģ®
    0.17
    Activations Density 0.010%

    No Known Activations