© 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. 142113
    Prev
    Next
    INDEX
    Explanations

    Usage of "as"

    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
    å¦Ĥæľīä¾µæĿĥ
    -0.27
    è¡Įç¨ĭ
    -0.27
    rop
    -0.27
    èĮ«èĮ«
    -0.27
    模èĮĥ
    -0.26
    typescript
    -0.26
    r
    -0.26
    Õµ
    -0.26
    uur
    -0.25
    ãĤŃãĥ£ãĥ³ãĥļãĥ¼ãĥ³
    -0.25
    POSITIVE LOGITS
     %-
    0.26
    åĤ¬çĶŁ
    0.24
    ведениÑı
    0.23
     mainland
    0.23
    bau
    0.23
     Davidson
    0.23
    Trou
    0.23
    mdir
    0.23
     Trouble
    0.23
    念
    0.23
    Activations Density 6.674%

    No Known Activations