© 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. 15008
    Prev
    Next
    INDEX
    Explanations

    chromatography techniques

    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
    ILED
    -0.21
    iren
    -0.20
     Shak
    -0.19
    åħ»èĢģ
    -0.19
    STANCE
    -0.19
    lish
    -0.19
     Keller
    -0.19
    oze
    -0.19
    lor
    -0.19
     accompanying
    -0.19
    POSITIVE LOGITS
    è¿ĩ滤
    0.37
    åĪĨ离
    0.29
     filtration
    0.25
    çŃĽéĢī
    0.25
     ÑĢаздел
    0.24
    滤
    0.24
    èIJĥ
    0.23
     filter
    0.23
     filtering
    0.23
     filtr
    0.23
    Activations Density 0.196%

    No Known Activations