© 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. 57293
    Prev
    Next
    INDEX
    Explanations

    colors

    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
     topic
    -0.28
    æ¸ħ
    -0.27
     Fluid
    -0.26
    管çIJĨä¸Ńå¿ĥ
    -0.26
    å®ı
    -0.26
    erator
    -0.26
    ç¼ĵæħ¢
    -0.25
    审
    -0.25
     plug
    -0.25
     exhibit
    -0.25
    POSITIVE LOGITS
    彩èī²
    0.36
     coloured
    0.29
    彩
    0.28
    stä
    0.28
     colours
    0.28
    /colors
    0.26
    绿èī²
    0.25
     colored
    0.25
     colors
    0.25
    colors
    0.25
    Activations Density 0.002%

    No Known Activations