© 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. 41031
    Prev
    Next
    INDEX
    Explanations

    talk

    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
    对å¾ħ
    -0.27
    ato
    -0.26
     yourself
    -0.26
     Laden
    -0.26
    è·ŁçĿĢ
    -0.24
    带åĬ¨
    -0.24
    lector
    -0.24
    isky
    -0.23
    quisite
    -0.23
    Limited
    -0.23
    POSITIVE LOGITS
     SSA
    0.28
    mania
    0.27
    infeld
    0.25
     hinge
    0.25
     Bermuda
    0.24
    dice
    0.24
     Plum
    0.24
     UIManager
    0.24
    Ĥæķ°
    0.23
    UDA
    0.23
    Activations Density 0.187%

    No Known Activations