© 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. 141472
    Prev
    Next
    INDEX
    Explanations

    Mixed conversations/technical snippets

    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
    ossa
    -0.29
    edly
    -0.27
     dialogs
    -0.26
    rolley
    -0.25
    LU
    -0.25
    (di
    -0.25
    icker
    -0.25
    åĪĨè¡Į
    -0.25
    nable
    -0.24
    LR
    -0.24
    POSITIVE LOGITS
    龸çİĭ
    0.25
     Expression
    0.25
    ivo
    0.25
    abd
    0.24
    主åĬ¨
    0.24
    iec
    0.24
    ryan
    0.24
    主åĭķ
    0.24
    槿
    0.23
     przec
    0.23
    Activations Density 96.515%

    No Known Activations