© 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. 57874
    Prev
    Next
    INDEX
    Explanations

    code

    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
    ixed
    -0.31
    rss
    -0.26
    idges
    -0.26
    SED
    -0.26
     ALTER
    -0.25
    èµĦæºIJåħ±äº«
    -0.25
    rolled
    -0.25
    indo
    -0.25
     commuter
    -0.24
    riage
    -0.24
    POSITIVE LOGITS
    çĥ¹
    0.29
    å±Ģå±Ģéķ¿
    0.28
    æĢ¨
    0.28
    å½Ī
    0.27
    æģ¨
    0.27
     вÑģÑĤÑĢеÑĩ
    0.26
    欢è¿İæĤ¨
    0.26
    竽
    0.26
    å¼ķæµģ
    0.25
    acha
    0.25
    Activations Density 0.042%

    No Known Activations