© 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. 107517
    Prev
    Next
    INDEX
    Explanations

    window

    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
    ër
    -0.27
    åĢŁè´·
    -0.27
     cons
    -0.25
    ä¼Ļ
    -0.25
    zin
    -0.24
    ä¸Ī夫
    -0.24
    è¿Ļæīįæĺ¯
    -0.24
    稽
    -0.24
     quadr
    -0.24
    缸å½ĵäºİ
    -0.24
    POSITIVE LOGITS
    _section
    0.26
     Sharma
    0.26
     SECTION
    0.25
    ооÑĢÑĥж
    0.25
    é«ĺ楼
    0.25
     Guerrero
    0.24
     curtain
    0.24
     Section
    0.24
     distress
    0.24
    tings
    0.24
    Activations Density 0.951%

    No Known Activations