© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 39998
    Prev
    Next
    INDEX
    Explanations

    legal/official documents

    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
    Not in Any Lists

    No Comments

    Negative Logits
     entered
    -0.40
     reported
    -0.39
     presented
    -0.38
     referenced
    -0.36
     stated
    -0.35
     supplied
    -0.35
     expressed
    -0.34
     recorded
    -0.34
     identified
    -0.34
     adopted
    -0.34
    POSITIVE LOGITS
     glance
    0.28
    äºı
    0.26
     bó
    0.26
     wax
    0.26
    DT
    0.26
     african
    0.26
     gadgets
    0.25
     sky
    0.25
     giants
    0.25
    DV
    0.25
    Activations Density 57.429%

    No Known Activations