© 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. 8213
    Prev
    Next
    INDEX
    Explanations

    technical/scientific documents

    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
    äºĨä¸Ģ
    -0.28
    çĮĹ
    -0.27
    ahkan
    -0.27
    åĭĴ
    -0.26
    åIJİçļĦ
    -0.25
    大çīĩ
    -0.25
     quán
    -0.25
    conversation
    -0.24
    -analytics
    -0.24
    ì¶
    -0.23
    POSITIVE LOGITS
     hWnd
    0.26
     Bio
    0.26
     Sol
    0.26
    ume
    0.26
    åºĨ幸
    0.25
     Insp
    0.25
     Trust
    0.25
     ÑĥвеÑĢ
    0.25
     Else
    0.25
    à¸ķร
    0.24
    Activations Density 0.001%

    No Known Activations