© 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. 87366
    Prev
    Next
    INDEX
    Explanations

    code or documentation

    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
     help
    -0.28
    itas
    -0.27
     Capital
    -0.26
     KS
    -0.26
    archy
    -0.26
     ahead
    -0.25
    finger
    -0.25
    åĪ°ä½į
    -0.25
    sett
    -0.25
     just
    -0.25
    POSITIVE LOGITS
    prene
    0.27
    çIJĨ解åĴĮ
    0.27
    Ĥ¬
    0.26
    simulate
    0.25
    -animate
    0.24
    âĦĭ
    0.24
    /AFP
    0.24
    xBF
    0.24
    theme
    0.24
     themes
    0.23
    Activations Density 0.001%

    No Known Activations