© 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. 111453
    Prev
    Next
    INDEX
    Explanations

    Scraped text fragments

    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
    å®ŀè´¨
    -0.28
    缴è¾ĸ
    -0.26
    ãĢħ
    -0.25
     padx
    -0.25
    .GeneratedValue
    -0.25
    essen
    -0.24
    기ëıĦ
    -0.24
    ooks
    -0.24
    alm
    -0.23
    seealso
    -0.23
    POSITIVE LOGITS
    anders
    0.28
    /WebAPI
    0.28
    *pi
    0.27
     Front
    0.25
     bal
    0.25
     Quantity
    0.25
    eno
    0.24
     ri
    0.24
     Current
    0.24
    *.
    0.24
    Activations Density 0.005%

    No Known Activations