© 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. 98027
    Prev
    Next
    INDEX
    Explanations

    .

    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
    acha
    -0.31
    egov
    -0.28
    ä¼łå¥ĩ
    -0.26
    acket
    -0.25
    mlin
    -0.25
     Formation
    -0.24
    èĽ®
    -0.24
    éĻ¢éĻ¢éķ¿
    -0.24
    FormatException
    -0.24
    Invocation
    -0.23
    POSITIVE LOGITS
    åĴĮåıijå±ķ
    0.29
     yet
    0.29
    åĴĮ社ä¼ļ
    0.27
    åĴĮåľ°åĮº
    0.26
    yet
    0.25
    å²Ĥ
    0.25
     last
    0.24
    orp
    0.24
    \\"
    0.24
    TED
    0.24
    Activations Density 0.005%

    No Known Activations