© 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. 8618
    Prev
    Next
    INDEX
    Explanations

    membrane

    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
    ÉIJ
    -0.27
    orca
    -0.24
    ardin
    -0.24
    iom
    -0.23
    è´¹
    -0.23
    Development
    -0.23
    è´¸
    -0.23
    åŃĹä½ĵ
    -0.23
    iously
    -0.23
    å¼ĢåıijèĢħ
    -0.23
    POSITIVE LOGITS
    oleon
    0.25
    zac
    0.25
    .Serve
    0.24
    è¢ĭ
    0.24
    -my
    0.24
    isphere
    0.24
    èĴ½
    0.23
    ULK
    0.23
    .Interface
    0.23
     MSD
    0.23
    Activations Density 0.049%

    No Known Activations