© 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. 8459
    Prev
    Next
    INDEX
    Explanations

    8

    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
    rieve
    -0.27
    yt
    -0.26
    ãĥ¼ãĤ¸
    -0.26
    åĺĮ
    -0.26
     âĪ
    -0.26
    æĻ¯
    -0.25
    åħļ
    -0.25
    æŃĩ
    -0.25
    monic
    -0.24
     ad
    -0.24
    POSITIVE LOGITS
     slashes
    0.29
    colon
    0.27
     assignment
    0.27
     colon
    0.27
    (':',
    0.27
     curly
    0.26
     circulation
    0.26
     dashes
    0.26
     assignments
    0.26
    ewise
    0.26
    Activations Density 0.011%

    No Known Activations