© 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. 12760
    Prev
    Next
    INDEX
    Explanations

    shortcuts and concessions

    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
    ãģĹãģ¾ãģĨ
    -0.21
    åŃ¦å®¶
    -0.20
    nge
    -0.18
    ãģ®ãģĮ
    -0.18
     Grat
    -0.18
    åѦ龸
    -0.18
    åıijå±ķåīįæĻ¯
    -0.17
    çĬį
    -0.17
    è¡ĮåĬ¨è®¡åĪĴ
    -0.17
    OLS
    -0.16
    POSITIVE LOGITS
    ../../../
    0.27
    ter
    0.25
    ../../
    0.23
    erator
    0.21
    ional
    0.21
    tere
    0.19
    alog
    0.18
    ativ
    0.18
    era
    0.18
    妤
    0.17
    Activations Density 0.005%

    No Known Activations