© 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. 8036
    Prev
    Next
    INDEX
    Explanations

    Re

    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
    人人
    -0.27
    erial
    -0.26
    liest
    -0.25
    çī¹æ´¾
    -0.25
     ksi
    -0.25
    xcc
    -0.25
    å®ĥæĺ¯
    -0.25
    parable
    -0.24
    ä¸ĢæĶ¯
    -0.24
    portun
    -0.24
    POSITIVE LOGITS
     facing
    0.31
    åĽŀ
    0.29
    è¿´
    0.28
    åijĨ
    0.28
     speed
    0.28
    æŁ¥éĺħ
    0.27
     breaking
    0.27
     addressing
    0.27
     finally
    0.27
    orget
    0.27
    Activations Density 0.002%

    No Known Activations