© 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
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 8681
    Prev
    Next
    INDEX
    Explanations

    university, college

    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
    dig
    -0.30
    ture
    -0.29
    IGH
    -0.27
    åĪĨéĴŁåIJİ
    -0.26
     dig
    -0.26
    湫
    -0.25
    ä»Ģ麽
    -0.25
    ниÑĩ
    -0.25
    个å¤ļ
    -0.25
     therm
    -0.25
    POSITIVE LOGITS
    æłı
    0.26
    ographies
    0.26
    pci
    0.26
    ordion
    0.25
     permalink
    0.25
    zano
    0.25
    ç®ħ
    0.25
    lbrakk
    0.25
    ложений
    0.24
    imonials
    0.24
    Activations Density 0.002%

    No Known Activations