© 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. 149684
    Prev
    Next
    INDEX
    Explanations

    Various topics

    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
    梵
    -0.25
    ä¹ĭåĬ¿
    -0.25
    åĪ°åºķæĺ¯
    -0.25
     Suff
    -0.25
    otope
    -0.24
    åĽłä¸ºå¥¹
    -0.24
    å®ļåIJij
    -0.24
    Append
    -0.23
    apa
    -0.23
    pan
    -0.23
    POSITIVE LOGITS
     Agent
    0.26
    .si
    0.25
    earned
    0.25
    icho
    0.25
     agent
    0.24
     intentional
    0.24
    TURE
    0.24
    ies
    0.24
     dó
    0.24
    endar
    0.23
    Activations Density 1.027%

    No Known Activations