© 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. 12699
    Prev
    Next
    INDEX
    Explanations

    convicted of crimes

    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
    imu
    -0.18
    è¾Ī
    -0.17
    chaft
    -0.16
    оÑĦ
    -0.16
    icipation
    -0.16
    aving
    -0.15
    íļĮìĿĺ
    -0.15
    flight
    -0.15
    ÅŁÄ±
    -0.15
    éªĿ
    -0.15
    POSITIVE LOGITS
    ity
    0.22
    rate
    0.17
    nel
    0.17
    urable
    0.17
    ive
    0.17
    ment
    0.16
    ierte
    0.16
    sss
    0.16
    ly
    0.16
    ively
    0.16
    Activations Density 0.010%

    No Known Activations