© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15006
    Prev
    Next
    INDEX
    Explanations

    marriage or death certificates

    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
    FilterWhere
    -0.25
    PropertyParams
    -0.25
    該使çĶ¨èĢħ
    -0.23
    ParallelGroup
    -0.21
    ä¸ĢæµģçļĦ
    -0.20
    CallableWrapper
    -0.20
    SplitOptions
    -0.20
    å¼Ĭ
    -0.20
    ä¸Ģæµģ
    -0.20
     proprié
    -0.20
    POSITIVE LOGITS
    è®°å½ķ
    0.31
    å§ĵåIJį
    0.26
     records
    0.26
    çĻ»è®°
    0.25
    Record
    0.25
    é¢Ĩåıĸ
    0.23
     record
    0.23
    åŁºæľ¬ä¿¡æģ¯
    0.23
    è¡Į
    0.23
    踪
    0.22
    Activations Density 0.122%

    No Known Activations