© 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. 150892
    Prev
    Next
    INDEX
    Explanations

    amid

    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
    åĨįä¹Łæ²¡æľī
    -0.27
    imbus
    -0.25
    èĥĮçĿĢ
    -0.25
    addock
    -0.25
    jen
    -0.25
     Roberts
    -0.24
    ipsis
    -0.24
     Middleton
    -0.24
     Judiciary
    -0.23
    åĨįè§ģ
    -0.23
    POSITIVE LOGITS
    æ¶Ł
    0.26
    atement
    0.25
     nationally
    0.24
    æģį
    0.24
    >}</
    0.23
    è¿Ļä¸ĢåĪĩ
    0.23
    ä¸įæĸŃåıijå±ķ
    0.23
     */,
    0.23
     tables
    0.23
    tables
    0.23
    Activations Density 0.109%

    No Known Activations