© 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. 40283
    Prev
    Next
    INDEX
    Explanations

    Code, measurements, technical details

    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
     racing
    -0.27
     &(
    -0.27
    (kernel
    -0.27
    Ñģла
    -0.27
    amps
    -0.26
    åı·çº¿
    -0.26
    aji
    -0.25
    WindowSize
    -0.25
    ä¼ļè§ģ
    -0.25
    çĤ¹éĴŁ
    -0.24
    POSITIVE LOGITS
     vale
    0.27
     Emer
    0.27
    Ĭ¶
    0.27
    Ster
    0.26
    elter
    0.26
    åŁºç¡Ģä¸Ĭ
    0.26
    yer
    0.25
     Palo
    0.25
    lander
    0.24
    å®ľ
    0.24
    Activations Density 0.091%

    No Known Activations