© 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. 25-TRANSCODER-HP
    7. 107611
    Prev
    Next
    INDEX
    Explanations

    Lack of knowledge/uncertainty

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å±ij
    -0.28
    èħº
    -0.26
     aspect
    -0.26
    ä½İ声
    -0.26
    aspect
    -0.26
    faces
    -0.25
     sw
    -0.25
     scenes
    -0.25
    åįĥ亿
    -0.25
    ä¸Ģ页
    -0.25
    POSITIVE LOGITS
    ecd
    0.26
    .isEnabled
    0.26
    太æŀģ
    0.26
     favour
    0.25
    è¿ĻéĩĮæĺ¯
    0.25
     IDM
    0.25
    ORE
    0.24
    çİĩè¾¾
    0.24
    åı¯ä¿¡
    0.23
    ¾
    0.23
    Activations Density 0.194%

    No Known Activations