© 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. 40193
    Prev
    Next
    INDEX
    Explanations

    wo

    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
    itur
    -0.26
    redirectToRoute
    -0.26
    UGIN
    -0.25
    åĪį
    -0.25
     desper
    -0.23
     neighb
    -0.23
    åı£æ°´
    -0.23
     doÄŁru
    -0.23
    ashboard
    -0.23
    ddf
    -0.23
    POSITIVE LOGITS
     Vog
    0.28
    ubb
    0.27
    ort
    0.27
    oting
    0.26
    oot
    0.25
    èĤĦ
    0.25
    ием
    0.25
    ooting
    0.25
    oti
    0.25
    ados
    0.24
    Activations Density 0.999%

    No Known Activations