© 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. 63450
    Prev
    Next
    INDEX
    Explanations

    close

    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
    çľĭå¾Ĺ
    -0.26
     Competition
    -0.26
    çĤ¹åĩ»æŁ¥çľĭ
    -0.25
    åĪ¹
    -0.25
     +(
    -0.25
    è¿¢
    -0.25
    Police
    -0.25
     Isles
    -0.24
    åĬ«
    -0.24
    Proof
    -0.24
    POSITIVE LOGITS
    mann
    0.27
    ä½İ碳
    0.26
    .fromJson
    0.24
    arbon
    0.24
     coat
    0.23
    leton
    0.23
    -around
    0.23
    bbe
    0.23
    WindowText
    0.23
     stays
    0.23
    Activations Density 16.826%

    No Known Activations