© 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. 2105
    Prev
    Next
    INDEX
    Explanations

    BPM, workflow, processes

    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
     Heights
    -0.25
    éĺµèIJ¥
    -0.25
    æĺŁç©º
    -0.23
    æĶĢçĻ»
    -0.23
    Touches
    -0.23
    OfFile
    -0.22
    ortho
    -0.22
     dent
    -0.22
    quipment
    -0.22
     Orth
    -0.22
    POSITIVE LOGITS
     BPM
    0.35
    æµģç¨ĭ
    0.33
    Govern
    0.28
     Chore
    0.28
    é¼ĵ
    0.28
     Workflow
    0.28
     process
    0.27
     Stateless
    0.27
     Govern
    0.26
     Governance
    0.26
    Activations Density 0.060%

    No Known Activations