© 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. 141134
    Prev
    Next
    INDEX
    Explanations

    News articles

    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
     stranger
    -0.25
    казалоÑģÑĮ
    -0.24
     LIABILITY
    -0.24
    å»¶æľŁ
    -0.24
     Learning
    -0.24
     pou
    -0.24
    é¢ĦåijĬ
    -0.24
    éĤĢ
    -0.23
     Stranger
    -0.23
    abis
    -0.23
    POSITIVE LOGITS
     Rica
    0.27
    ndo
    0.27
     profession
    0.26
    iage
    0.25
    çĬĬ
    0.25
     capturing
    0.24
    scenario
    0.24
     killed
    0.24
    casting
    0.23
    isting
    0.23
    Activations Density 0.837%

    No Known Activations