© 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. 35-TRANSCODER-HP
    7. 38694
    Prev
    Next
    INDEX
    Explanations

    technical texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     bay
    -0.29
     prior
    -0.29
     boasted
    -0.27
     boast
    -0.27
     shri
    -0.26
     tweaked
    -0.26
     Tribe
    -0.26
     boasts
    -0.26
     boasting
    -0.26
     brains
    -0.25
    POSITIVE LOGITS
    adia
    0.38
    adf
    0.36
    dad
    0.36
    adamente
    0.36
    adian
    0.35
    adc
    0.34
    adx
    0.32
    adin
    0.31
    ade
    0.31
    ados
    0.31
    Activations Density 0.862%

    No Known Activations