© 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. 108414
    Prev
    Next
    INDEX
    Explanations

    Buddhism-related texts

    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
    声
    -0.27
    eded
    -0.26
    cond
    -0.26
    -member
    -0.25
    xed
    -0.25
    .nih
    -0.24
    èģ²
    -0.24
    PIN
    -0.24
    prm
    -0.24
    upon
    -0.24
    POSITIVE LOGITS
    yt
    0.31
    ants
    0.29
    ãģ®ãģ¯
    0.27
     candles
    0.27
     practiced
    0.26
    ant
    0.26
     practice
    0.25
    rat
    0.25
    STER
    0.25
     yog
    0.25
    Activations Density 1.189%

    No Known Activations