© 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. 33-TRANSCODER-HP
    7. 54018
    Prev
    Next
    INDEX
    Explanations

    Names and locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    antic
    -0.37
    NECT
    -0.26
    ALTH
    -0.26
    RET
    -0.26
    Tw
    -0.26
    acd
    -0.25
    ATRIX
    -0.25
    equip
    -0.25
     sip
    -0.25
    ections
    -0.25
    POSITIVE LOGITS
    æĸ¹æīį
    0.26
    æĹ¥å¤ľ
    0.26
    æĥħèĬĤ
    0.26
    åĮĿ
    0.25
    èĨº
    0.25
    èĪŀåı°ä¸Ĭ
    0.25
     tales
    0.24
    /framework
    0.24
     Namespace
    0.24
    DBus
    0.23
    Activations Density 0.005%

    No Known Activations