© 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. 54774
    Prev
    Next
    INDEX
    Explanations

    Franc

    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
    stakes
    -0.29
    ache
    -0.26
    kee
    -0.26
    çºł
    -0.26
    æķĪ
    -0.25
    æĸŃ
    -0.25
     loaf
    -0.25
     rs
    -0.25
    tone
    -0.25
    town
    -0.24
    POSITIVE LOGITS
    eration
    0.28
    大æĪĺ
    0.28
    ement
    0.27
    /documentation
    0.27
    ilion
    0.25
    ocities
    0.24
    encies
    0.24
    ocity
    0.24
    itaire
    0.24
     Sob
    0.24
    Activations Density 0.002%

    No Known Activations