© 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. 12078
    Prev
    Next
    INDEX
    Explanations

    sock or socket

    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
    ãĤĤãģĨ
    -0.17
    ubar
    -0.16
    icont
    -0.16
     Uph
    -0.15
    åĽ½ç±į
    -0.15
    æªİ
    -0.15
    æѤåĪ»
    -0.15
    opsis
    -0.15
    BUFF
    -0.15
    wed
    -0.15
    POSITIVE LOGITS
    sis
    0.22
    ivity
    0.20
    sWith
    0.20
    ey
    0.19
    busters
    0.19
    ify
    0.18
    ingly
    0.18
    tober
    0.18
    pedia
    0.17
    ively
    0.17
    Activations Density 0.014%

    No Known Activations