© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 109582
    Prev
    Next
    INDEX
    Explanations

    numerical measurements

    np_max-act-logits · gemini-2.0-flash
    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
    Negative Logits
    riet
    -0.29
     moderation
    -0.26
     face
    -0.26
     deficit
    -0.26
    amide
    -0.25
    (face
    -0.25
    éĿ¢
    -0.25
    IODevice
    -0.25
    ame
    -0.25
     overlay
    -0.25
    POSITIVE LOGITS
    ä¼ļåıijçĶŁ
    0.27
    OLA
    0.27
    successful
    0.26
    dcc
    0.26
    _occ
    0.25
    inka
    0.24
    åħļæĢ»
    0.24
    pipe
    0.24
    	tb
    0.24
    Stop
    0.24
    Activations Density 0.911%

    No Known Activations