© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1637
    Prev
    Next
    INDEX
    Explanations

    direction on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    oute
    -0.26
    ife
    -0.26
    并
    -0.25
    yre
    -0.25
    fe
    -0.25
    wx
    -0.25
    ite
    -0.24
    lo
    -0.23
    por
    -0.23
    并äºİ
    -0.23
    POSITIVE LOGITS
    -interface
    0.23
     Interested
    0.22
    å±Ĥåĩº
    0.22
     breakout
    0.21
    磧
    0.21
    adero
    0.21
     APPLY
    0.21
     upstream
    0.20
    baar
    0.20
    ncy
    0.20
    Activations Density 0.195%

    No Known Activations