© 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. 16795
    Prev
    Next
    INDEX
    Explanations

    stereo sound and chemistry

    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
    sWith
    -0.23
    OrCreate
    -0.19
    ired
    -0.18
    kins
    -0.18
    åĴĮåıijå±ķ
    -0.18
    edList
    -0.18
    soever
    -0.17
    isters
    -0.17
    stown
    -0.17
    skin
    -0.16
    POSITIVE LOGITS
    æĪĸå¤ļ
    0.33
    åĮĸè¿Ľç¨ĭ
    0.20
    殿ä¸ĭ
    0.18
    /single
    0.18
    æł¼å±Ģ
    0.18
     знаÑĩиÑĤ
    0.18
    大å±Ģ
    0.17
    éĻĽ
    0.17
     babes
    0.16
    etten
    0.16
    Activations Density 0.005%

    No Known Activations