© 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. 8957
    Prev
    Next
    INDEX
    Explanations

    environment variables

    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
    еÑģÑĤво
    -0.26
    ba
    -0.25
    íĶĦë¡ľê·¸ëŀ¨
    -0.25
    주ëĬĶ
    -0.25
    sign
    -0.25
    æĶ¾åģĩ
    -0.25
    èĥª
    -0.25
     dign
    -0.25
     sign
    -0.25
    oi
    -0.24
    POSITIVE LOGITS
    .env
    0.29
    åĮĹ约
    0.28
    env
    0.28
    éĺ²
    0.27
    çĶŁæ´»çݯå¢ĥ
    0.27
    dotenv
    0.26
    çݯå¢ĥä¿ĿæĬ¤
    0.26
    ENV
    0.26
    å°½æĹ©
    0.25
    urable
    0.25
    Activations Density 0.001%

    No Known Activations