© 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. 107508
    Prev
    Next
    INDEX
    Explanations

    of

    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
     absor
    -0.28
     mee
    -0.26
     Tender
    -0.25
     nth
    -0.24
    ä½Ŀ
    -0.24
    å¢ŀè¿Ľ
    -0.24
     encour
    -0.24
     maint
    -0.24
    dit
    -0.24
    .TXT
    -0.24
    POSITIVE LOGITS
    pper
    0.28
    wards
    0.27
    两ç§į
    0.26
    ulas
    0.26
    ensions
    0.25
    .dimension
    0.24
     drive
    0.24
    track
    0.24
    atures
    0.24
     Define
    0.24
    Activations Density 7.523%

    No Known Activations