© 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. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 108355
    Prev
    Next
    INDEX
    Explanations

    complex and uncertain statements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ehr
    -0.27
    izzy
    -0.27
    çĵ¶é¢Ī
    -0.27
    æ´²
    -0.26
    ç²¾
    -0.24
    ä½IJ
    -0.24
    uzzi
    -0.24
    èĩªå·±çļĦ
    -0.24
    è°ĥçļ®
    -0.24
    rut
    -0.24
    POSITIVE LOGITS
    åĸĿäºĨ
    0.30
    ä¹°äºĨ
    0.28
    built
    0.26
    agli
    0.26
    AndPassword
    0.25
    ForObject
    0.25
     separated
    0.25
     built
    0.24
    ibel
    0.24
     adjoining
    0.23
    Activations Density 40.434%

    No Known Activations