© 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. 14556
    Prev
    Next
    INDEX
    Explanations

    divides or separates into parts

    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
    è°Ģ
    -0.18
    itude
    -0.17
    ienie
    -0.17
    ани
    -0.16
     اÙĦÙĪاØŃد
    -0.15
    çĺķ
    -0.15
    rong
    -0.15
    ÑģÑĭ
    -0.15
     bigot
    -0.15
    èĵij
    -0.15
    POSITIVE LOGITS
    /div
    0.23
    èĥľè´Ł
    0.21
    tures
    0.20
    ä»ij
    0.20
     divides
    0.20
     between
    0.20
    /se
    0.19
    zelf
    0.18
    tok
    0.18
    å¼ĢæĿ¥
    0.18
    Activations Density 0.050%

    No Known Activations