© 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. 1458
    Prev
    Next
    INDEX
    Explanations

    financial lending activities

    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
     Cann
    -0.27
     Mushroom
    -0.27
     intellect
    -0.26
     Beer
    -0.26
     charismatic
    -0.25
     Bangkok
    -0.25
     Geological
    -0.24
     guessed
    -0.23
    éĤĥ
    -0.23
    æł¹æį®èĩªå·±
    -0.23
    POSITIVE LOGITS
    å¤įèĭı
    0.31
    æĻ®æĥł
    0.31
    纾
    0.31
    çĽij管
    0.30
    redit
    0.30
    æĶ¿çŃĸ
    0.30
    ä¿¡è´·
    0.30
     credit
    0.29
     Mortgage
    0.29
    å¾ģä¿¡
    0.29
    Activations Density 0.007%

    No Known Activations