© 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. 31-TRANSCODER-HP
    7. 19272
    Prev
    Next
    INDEX
    Explanations

    Summaries or introductions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IST
    -0.27
    isd
    -0.26
    主ä¹ī
    -0.26
    itre
    -0.26
    istas
    -0.26
    ist
    -0.26
    çªĴæģ¯
    -0.25
    ishes
    -0.25
    .bo
    -0.25
     old
    -0.24
    POSITIVE LOGITS
     Created
    0.36
     creation
    0.31
     practice
    0.31
    createView
    0.31
     Creation
    0.31
    -created
    0.31
     creations
    0.30
    created
    0.30
     concept
    0.30
     created
    0.30
    Activations Density 1.938%

    No Known Activations