© 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. 56306
    Prev
    Next
    INDEX
    Explanations

    exp

    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
    è¯Ħæµĭ
    -0.26
    xis
    -0.26
    ingham
    -0.26
    æĺ¥å¤©
    -0.24
    峪
    -0.24
     fog
    -0.24
    ILT
    -0.24
     traff
    -0.24
    åħĪè¿ĽçļĦ
    -0.23
    æµ·æ¹¾
    -0.23
    POSITIVE LOGITS
    s
    0.56
    sist
    0.30
    sip
    0.30
    sampling
    0.28
    sand
    0.28
    sheets
    0.27
     seg
    0.26
    sad
    0.26
    squ
    0.25
    sar
    0.25
    Activations Density 0.006%

    No Known Activations