© 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. 19254
    Prev
    Next
    INDEX
    Explanations

    both

    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
     Both
    -0.47
    both
    -0.45
     both
    -0.45
    Both
    -0.44
    两èĢħ
    -0.42
    è¿Ļ两ç§į
    -0.39
    åīįèĢħ
    -0.38
     ambos
    -0.35
    äºĮèĢħ
    -0.35
     beide
    -0.35
    POSITIVE LOGITS
     mats
    0.33
     rectangles
    0.31
     surfaces
    0.30
     sheets
    0.30
    sockets
    0.30
    èĢģ大
    0.28
    mite
    0.27
     triangles
    0.27
     spirits
    0.27
     containers
    0.27
    Activations Density 0.055%

    No Known Activations