© 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. 27-TRANSCODER-HP
    7. 9297
    Prev
    Next
    INDEX
    Explanations

    Unusual/random texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cruc
    -0.28
     rider
    -0.26
     Senior
    -0.25
    ruc
    -0.24
    ró
    -0.24
     Official
    -0.24
    xCD
    -0.24
     Together
    -0.24
     senior
    -0.24
    Ac
    -0.24
    POSITIVE LOGITS
    大家
    0.32
    大家åĪĨ享
    0.27
    urve
    0.26
    anmar
    0.26
    åĺ´è§Ĵ
    0.26
    emarks
    0.25
    UV
    0.25
    ayout
    0.25
     Pattern
    0.25
    yped
    0.25
    Activations Density 0.016%

    No Known Activations