© 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. 14571
    Prev
    Next
    INDEX
    Explanations

    annual, perennial, deciduous

    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
     LSB
    -0.20
    upe
    -0.20
    åĬ¡
    -0.19
    ä¸įä¸ĭ
    -0.19
    diff
    -0.19
    åı«å£°
    -0.19
    èŀĥèŁ¹
    -0.18
    SCP
    -0.18
    å®ļçĤ¹
    -0.17
    åĭĻ
    -0.17
    POSITIVE LOGITS
    åĩ¡äºĭ
    0.21
    vents
    0.20
    afil
    0.19
    lang
    0.19
    assed
    0.19
     bedding
    0.19
    ismo
    0.19
    ypes
    0.18
    particles
    0.18
    asion
    0.18
    Activations Density 0.003%

    No Known Activations