© 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. 23-TRANSCODER-HP
    7. 24341
    Prev
    Next
    INDEX
    Explanations

    power sources

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     incent
    -0.31
    åľ¨æ¸¸æĪıä¸Ń
    -0.25
    ób
    -0.25
    ]|
    -0.24
    åĭĭ
    -0.23
    Tem
    -0.23
    ownt
    -0.23
    uckle
    -0.23
    ragments
    -0.23
     bach
    -0.23
    POSITIVE LOGITS
    .tap
    0.28
    æijĩ头
    0.27
     brush
    0.27
    -domain
    0.26
     manual
    0.26
    éĹŃ
    0.26
     ambient
    0.25
    lette
    0.25
    让æĪij们
    0.24
    æīĵå¼Ģ
    0.24
    Activations Density 0.029%

    No Known Activations