© 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. 88490
    Prev
    Next
    INDEX
    Explanations

    Numbers

    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
    麽
    -0.28
    åİŁæľī
    -0.26
    çIJĨæĥ³
    -0.25
     Pent
    -0.24
    åIJĦç§į
    -0.24
    }?
    -0.24
    ä¸įæĺİçĻ½
    -0.24
    饥饿
    -0.24
    çIJĨæĥ³çļĦ
    -0.23
    nard
    -0.23
    POSITIVE LOGITS
    èĩ³ä»Ĭ
    0.35
    present
    0.33
     today
    0.32
     present
    0.32
     Present
    0.31
    .present
    0.31
    roma
    0.30
     Today
    0.29
    Present
    0.28
    Today
    0.27
    Activations Density 0.027%

    No Known Activations