© 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. 23-TRANSCODER-HP
    7. 24568
    Prev
    Next
    INDEX
    Explanations

    image/photo

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     OTHERWISE
    -0.28
    主ç¼ĸ
    -0.26
    çľĭå®Į
    -0.26
    istar
    -0.25
     din
    -0.25
    èµı
    -0.25
    æł¸å®ļ
    -0.25
    pons
    -0.25
    ½
    -0.24
     vign
    -0.24
    POSITIVE LOGITS
    ç§ij缮
    0.27
    gether
    0.27
    æĤ²
    0.25
    RAL
    0.25
    genes
    0.24
    âĢ¹
    0.24
    دÙĬØ«
    0.24
    Hell
    0.24
    å¯Ħ
    0.23
    ChartData
    0.23
    Activations Density 0.006%

    No Known Activations