© 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. 130250
    Prev
    Next
    INDEX
    Explanations

    Names and photo captions

    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
    pring
    -0.27
    RING
    -0.26
     ARTICLE
    -0.26
    bots
    -0.25
    esis
    -0.25
    ring
    -0.25
     txt
    -0.25
     Heller
    -0.25
    norm
    -0.25
    obot
    -0.24
    POSITIVE LOGITS
    æŃ£åľ¨
    0.34
     Wikimedia
    0.32
    ä¾ĽåĽ¾
    0.32
    åīįæĻ¯
    0.32
     figure
    0.32
     Flickr
    0.32
    æŃ£åľ¨è¿Ľè¡Į
    0.31
    æŃ£å¤Ħäºİ
    0.30
     seated
    0.29
     Shutterstock
    0.29
    Activations Density 0.051%

    No Known Activations