© 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. 27-TRANSCODER-HP
    7. 9448
    Prev
    Next
    INDEX
    Explanations

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åľ¨éĤ£éĩĮ
    -0.33
    éĤ£éĩĮ
    -0.28
     æĽ
    -0.25
    udge
    -0.25
    ritt
    -0.24
    .UNKNOWN
    -0.24
    laden
    -0.24
    +xml
    -0.23
    -gap
    -0.23
    leet
    -0.23
    POSITIVE LOGITS
    ä¸ŃåŃĺåľ¨çļĦ
    0.29
    elong
    0.26
    çİ°æľīçļĦ
    0.25
    ket
    0.25
    æĻĤãģ«ãģ¯
    0.24
    kt
    0.24
    åĨħç½®
    0.24
    æľĢæĸ°
    0.24
    çīŁ
    0.24
    çİ°æľī
    0.24
    Activations Density 0.009%

    No Known Activations