© 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. 64385
    Prev
    Next
    INDEX
    Explanations

    Code and URLs

    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
    ãĤĥ
    -0.27
     há»ĵi
    -0.25
     [].
    -0.25
     f
    -0.24
    ans
    -0.24
     micro
    -0.24
    æłĩé¢ĺ
    -0.24
    åѦåŃIJ
    -0.23
     '{}
    -0.23
     scept
    -0.23
    POSITIVE LOGITS
    itary
    0.26
    wg
    0.25
    perature
    0.25
    æ»Ĥ
    0.25
     Declarations
    0.24
    emme
    0.24
    éĢĤå½ĵ
    0.24
    rary
    0.24
     closeButton
    0.24
    ervo
    0.24
    Activations Density 2.242%

    No Known Activations