© 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. 56683
    Prev
    Next
    INDEX
    Explanations

    Dates of service/lifespan

    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
    clide
    -0.28
    驶
    -0.27
    ^(
    -0.27
    rove
    -0.26
    MJ
    -0.26
    _phase
    -0.25
     Mesa
    -0.25
     Composer
    -0.25
    GCC
    -0.24
    udos
    -0.24
    POSITIVE LOGITS
    å¼ŁåħĦ
    0.28
    contest
    0.27
     contest
    0.27
    NotSupportedException
    0.26
    æīĢ说
    0.26
    æ¹Ķ
    0.26
    åħ¬åħ±åį«çĶŁ
    0.25
    yz
    0.24
    å¯Ħ
    0.24
    æīĢèĥ½
    0.24
    Activations Density 0.002%

    No Known Activations