© 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
    2. Qwen3-4B
    3. 27-TRANSCODER-HP
    4. 57112
    Prev
    Next
    INDEX
    Explanations

    proximity

    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
    .CreateInstance
    -0.27
    é¹°
    -0.27
    {text
    -0.27
    .newInstance
    -0.25
    ÅĽcie
    -0.25
    igm
    -0.23
    ength
    -0.23
    éĺ²æĬ¤
    -0.23
    ButtonText
    -0.23
     mücadele
    -0.23
    POSITIVE LOGITS
     him
    0.30
    æĪĸå°Ĩ
    0.30
     //~
    0.28
    å°ļ书
    0.27
    layer
    0.27
     whim
    0.26
    èħ±
    0.26
    ause
    0.26
     them
    0.26
    oman
    0.26
    Activations Density 0.005%

    No Known Activations