© 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. 18-TRANSCODER-HP
    7. 88783
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ingly
    -0.25
    æķ°ç»Ħ
    -0.25
    icorn
    -0.25
    gresql
    -0.25
     infiltr
    -0.24
    亥
    -0.24
    èĬĤæ°´
    -0.24
    æŃ¤äºº
    -0.23
    icum
    -0.23
    stalk
    -0.23
    POSITIVE LOGITS
    ĶĦ
    0.30
    社ä¼ļåıijå±ķ
    0.27
     essentials
    0.27
    ine
    0.26
    DidLoad
    0.26
     Essential
    0.24
    amos
    0.24
    aff
    0.24
    decorators
    0.24
     essential
    0.23
    Activations Density 17.617%

    No Known Activations