© 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. 16796
    Prev
    Next
    INDEX
    Explanations

    expresses strong expletives

    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
    mega
    -0.17
    uez
    -0.17
    åĭĥåĭĥ
    -0.15
    صÙĦ
    -0.15
     fucking
    -0.15
    EGIN
    -0.15
    èĹľ
    -0.15
    ÈĽi
    -0.15
    oop
    -0.15
    iface
    -0.15
    POSITIVE LOGITS
    ety
    0.20
    iness
    0.20
    ery
    0.18
    able
    0.18
    ified
    0.18
    smith
    0.17
    sa
    0.17
    ÑĩаÑģ
    0.17
    ERY
    0.17
    ian
    0.17
    Activations Density 0.003%

    No Known Activations