© 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. 40769
    Prev
    Next
    INDEX
    Explanations

    Code

    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
    åķĨ
    -0.32
     commerc
    -0.26
    ikh
    -0.25
    orks
    -0.25
    ambre
    -0.25
    AndView
    -0.24
    arna
    -0.24
    ä¸ĢæĿ¡
    -0.24
    {n
    -0.24
    oyal
    -0.23
    POSITIVE LOGITS
    åħ»
    0.26
     scor
    0.26
     AAP
    0.25
    çĪ±
    0.25
    stand
    0.25
     discour
    0.25
     dishwasher
    0.24
    -da
    0.24
    缶
    0.24
    olk
    0.24
    Activations Density 0.079%

    No Known Activations