© 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. 22-TRANSCODER-HP
    7. 129618
    Prev
    Next
    INDEX
    Explanations

    Math and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cancel
    -0.27
     vs
    -0.26
     versus
    -0.26
     Yours
    -0.26
     compared
    -0.25
     \`
    -0.25
    è¿Ļä¸Ģ次
    -0.24
     hypert
    -0.24
     happ
    -0.24
    ä½ıäºĨ
    -0.24
    POSITIVE LOGITS
     BCH
    0.26
    幡
    0.25
    den
    0.25
    .major
    0.24
    .CR
    0.24
    å¹¿æ³ĽçļĦ
    0.24
    ffen
    0.23
    peria
    0.23
    &R
    0.23
    IPH
    0.23
    Activations Density 0.002%

    No Known Activations