© 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. 150960
    Prev
    Next
    INDEX
    Explanations

    since [year]

    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
    å¹´åīį
    -0.28
    æľŁéĹ´
    -0.28
    åľ°ä¸Ń
    -0.27
    æŶéĹ´åĨħ
    -0.27
    favicon
    -0.27
    æĿ¡ä»¶ä¸ĭ
    -0.27
     keyof
    -0.26
    失
    -0.26
     Macron
    -0.26
    ä¸Ĭåīį
    -0.25
    POSITIVE LOGITS
    erah
    0.35
    å®ĺæĸ¹
    0.30
     subsequent
    0.28
     official
    0.28
    orz
    0.26
     Official
    0.26
    çľģ级
    0.25
     explosive
    0.25
     institutional
    0.24
    å¼Ħ
    0.24
    Activations Density 0.052%

    No Known Activations