© 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. 107339
    Prev
    Next
    INDEX
    Explanations

    Code-related content

    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
     tons
    -0.26
     discretion
    -0.26
    dux
    -0.25
    ä¼ijåģĩ
    -0.25
    sole
    -0.24
    åºķèķ´
    -0.24
     showcased
    -0.24
    WAY
    -0.24
    ä¸ĭåıij
    -0.24
    annah
    -0.23
    POSITIVE LOGITS
    orias
    0.31
    oria
    0.27
    åħ¬
    0.26
    æľ¬ç½ij
    0.26
    _lua
    0.25
    ories
    0.25
    cis
    0.24
    иков
    0.24
    ].[
    0.24
     facing
    0.24
    Activations Density 0.018%

    No Known Activations