© 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. 41061
    Prev
    Next
    INDEX
    Explanations

    enroll

    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
    éķĩ
    -0.25
    两èĢħ
    -0.25
    oble
    -0.25
     velvet
    -0.25
    onation
    -0.24
    è¡
    -0.24
    åĪ©çī©
    -0.24
    erable
    -0.24
    .sb
    -0.24
    izard
    -0.24
    POSITIVE LOGITS
    rete
    0.31
    ä¼ļå±ķ
    0.29
    anse
    0.27
    dur
    0.26
    iture
    0.26
     Murphy
    0.26
    çıŃ
    0.26
     Judgment
    0.26
    å±ķ
    0.25
     Playground
    0.25
    Activations Density 2.160%

    No Known Activations