© 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. 24-TRANSCODER-HP
    7. 151121
    Prev
    Next
    INDEX
    Explanations

    jobs/employment

    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
    管çIJĨåijĺ
    -0.28
     Efficient
    -0.27
     sled
    -0.26
    åĬŀ好
    -0.25
    ftar
    -0.25
    feito
    -0.24
    å®ļæľŁ
    -0.24
    è¡Ģ
    -0.24
     tempList
    -0.23
    olem
    -0.23
    POSITIVE LOGITS
     Mell
    0.28
    ippet
    0.28
    Initial
    0.28
    verty
    0.27
    .Of
    0.27
    thesis
    0.26
     Initial
    0.26
    assy
    0.26
    entes
    0.26
    åı£è¢ĭ
    0.25
    Activations Density 0.122%

    No Known Activations