© 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. 63963
    Prev
    Next
    INDEX
    Explanations

    Sed

    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
    ication
    -0.27
    pling
    -0.27
    端æŃ£
    -0.27
    agr
    -0.25
    ite
    -0.25
    lict
    -0.25
     central
    -0.24
     reference
    -0.24
    sts
    -0.24
    HS
    -0.24
    POSITIVE LOGITS
    OOM
    0.29
    omen
    0.29
     [[]
    0.29
     dÃły
    0.27
    bounds
    0.26
    ä»Ģä¹Īåij¢
    0.26
    æıIJ款
    0.25
    ToBounds
    0.25
    emble
    0.25
     thicker
    0.25
    Activations Density 37.382%

    No Known Activations