© 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. 109062
    Prev
    Next
    INDEX
    Explanations

    Non-English words

    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
    åı¤ä»Ĭ
    -0.32
    orna
    -0.28
    sci
    -0.27
    RACT
    -0.26
    ock
    -0.25
    缨
    -0.25
    |)↵
    -0.24
    humidity
    -0.24
    gue
    -0.24
    磴
    -0.24
    POSITIVE LOGITS
    çľ¼
    0.29
    ä»ĺè´¹
    0.26
    ä»ĺ
    0.26
    æĻļéĹ´
    0.25
     something
    0.25
     kü
    0.24
     Something
    0.24
    aser
    0.24
    β
    0.24
    å¹´ä¸ĭåįĬå¹´
    0.23
    Activations Density 0.885%

    No Known Activations