© 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. 33-TRANSCODER-HP
    7. 54735
    Prev
    Next
    INDEX
    Explanations

    Pal

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æīĴ
    -0.26
    -neck
    -0.24
    obil
    -0.24
    ola
    -0.24
    ambi
    -0.24
    æĭħä¿Ŀ
    -0.24
     Plaza
    -0.23
    èĢ½è¯¯
    -0.23
    vergence
    -0.23
     Arch
    -0.23
    POSITIVE LOGITS
    ril
    0.31
    msp
    0.28
    rics
    0.28
    rus
    0.28
    ri
    0.27
    mapper
    0.25
    nants
    0.25
    ris
    0.25
    ato
    0.25
    arus
    0.25
    Activations Density 0.010%

    No Known Activations