© 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. 24-TRANSCODER-HP
    7. 150664
    Prev
    Next
    INDEX
    Explanations

    Location related words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     for
    -0.45
     длÑı
    -0.40
    对äºİ
    -0.40
     untuk
    -0.38
    ForObject
    -0.37
    èĢĮ对äºİ
    -0.37
    for
    -0.36
     voor
    -0.36
     für
    -0.35
    对ä»ĸ
    -0.35
    POSITIVE LOGITS
     elsewhere
    0.39
     wherever
    0.36
    åľ¨åĵªéĩĮ
    0.36
     everywhere
    0.35
    åľ¨æĹ¥æľ¬
    0.34
    åľ¨ä¸Ģ个
    0.34
    åľ¨å½ĵåľ°
    0.34
    åľ¨ç¾İåĽ½
    0.32
    åIJĦåľ°
    0.31
     anywhere
    0.31
    Activations Density 1.006%

    No Known Activations