© 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. 24-TRANSCODER-HP
    7. 150688
    Prev
    Next
    INDEX
    Explanations

    America

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¼¼ä¹İ
    -0.28
     conceptual
    -0.27
    å¾ģæľį
    -0.26
     (?)
    -0.25
     ecc
    -0.25
     alt
    -0.25
     conce
    -0.25
    mium
    -0.24
    ophil
    -0.24
     Dam
    -0.24
    POSITIVE LOGITS
    åĬłå¿«å»ºè®¾
    0.32
     America
    0.30
     communities
    0.29
     families
    0.29
     competit
    0.28
     job
    0.28
     American
    0.27
    illions
    0.26
     taxpayer
    0.26
    America
    0.26
    Activations Density 1.636%

    No Known Activations