© 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. 15863
    Prev
    Next
    INDEX
    Explanations

    session and session-specific configurations

    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
    asher
    -0.20
    artisan
    -0.20
    ç±į
    -0.19
    .opensource
    -0.19
    éri
    -0.19
    habi
    -0.19
    Scaler
    -0.19
    ç¨Ģ缺
    -0.19
    aters
    -0.18
    ptest
    -0.18
    POSITIVE LOGITS
     session
    0.37
     sessions
    0.33
     getSession
    0.30
     Session
    0.30
    Session
    0.30
    .Session
    0.28
     sess
    0.27
     SESSION
    0.26
     sessionId
    0.26
    session
    0.26
    Activations Density 0.410%

    No Known Activations