© 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. 130203
    Prev
    Next
    INDEX
    Explanations

    Temporal succession/continuation

    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
    pired
    -0.30
    åIJ¦
    -0.30
    iger
    -0.29
    iov
    -0.26
    ynamics
    -0.26
    hv
    -0.26
    æĺĵ
    -0.26
    èĵ¬åĭĥåıijå±ķ
    -0.25
    çIJ¼
    -0.25
    aron
    -0.25
    POSITIVE LOGITS
    å¤ľéĹ´
    0.28
     outlets
    0.27
     halves
    0.26
     atrás
    0.26
    -même
    0.26
    _SPLIT
    0.25
    -sidebar
    0.25
    -thirds
    0.25
    ä¸ĢåĪĻ
    0.25
    为æĬĵ
    0.24
    Activations Density 5.471%

    No Known Activations