© 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. 14-TRANSCODER-HP
    7. 40936
    Prev
    Next
    INDEX
    Explanations

    data models

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ipples
    -0.33
    aroo
    -0.33
    åĴ©
    -0.30
    å¤įä»ĩ
    -0.28
     powering
    -0.27
    å±ij
    -0.26
    沧
    -0.26
    OrNil
    -0.26
    olith
    -0.25
     addChild
    -0.25
    POSITIVE LOGITS
     åIJį
    0.29
     modeling
    0.27
    -inter
    0.27
     Stay
    0.26
     Guess
    0.25
     modeled
    0.25
     modelling
    0.25
    Dep
    0.25
     models
    0.25
     stay
    0.25
    Activations Density 1.035%

    No Known Activations