© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 9677
    Prev
    Next
    INDEX
    Explanations

    and,

    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
    Negative Logits
    encoded
    -0.29
    åĪº
    -0.27
    Encoded
    -0.25
    ħ§
    -0.25
    ensus
    -0.25
     Herc
    -0.24
    -fill
    -0.24
    æĵ¦
    -0.24
    UCT
    -0.24
    /env
    -0.24
    POSITIVE LOGITS
    æĽ´
    0.33
    æĽ´å®¹æĺĵ
    0.33
     nicer
    0.31
    ãĤĤãģ£ãģ¨
    0.28
     considerably
    0.28
     less
    0.28
    andum
    0.27
     more
    0.27
    æĽ´åĬł
    0.26
     stricter
    0.26
    Activations Density 0.005%

    No Known Activations