© 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. 25-TRANSCODER-HP
    7. 107881
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olars
    -0.27
    odem
    -0.26
    ICO
    -0.25
    éľĸ
    -0.25
     Wid
    -0.24
    èĥĮ
    -0.24
    ä¹ĭäºĭ
    -0.24
     Relief
    -0.24
    æĻ¾
    -0.23
    Rep
    -0.23
    POSITIVE LOGITS
    èĥĥèĤł
    0.28
    hoff
    0.27
     Criterion
    0.26
    -paying
    0.26
     curated
    0.26
    å·¥åķĨå±Ģ
    0.25
    iani
    0.24
     hj
    0.24
    GAN
    0.24
     Hours
    0.23
    Activations Density 0.049%

    No Known Activations

    This feature has no known activations.