© 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. 111658
    Prev
    Next
    INDEX
    Explanations

    s

    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
     sust
    -0.27
    thic
    -0.27
    ein
    -0.27
    e
    -0.27
    ster
    -0.27
     associated
    -0.26
    asure
    -0.26
    t
    -0.26
    tal
    -0.26
    o
    -0.25
    POSITIVE LOGITS
    ively
    0.34
    lightly
    0.32
    ingly
    0.31
    åį¡æĭī
    0.27
    caffold
    0.26
    éIJĺ
    0.26
    weeney
    0.26
    ugar
    0.25
    å®īä¸ľå°¼
    0.25
    åĮ»çĸĹæľºæŀĦ
    0.24
    Activations Density 0.209%

    No Known Activations