© 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. 38781
    Prev
    Next
    INDEX
    Explanations

    MacBook

    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
    CLU
    -0.30
    RAR
    -0.29
    ioni
    -0.29
    _lite
    -0.28
    DL
    -0.28
    LAG
    -0.28
    ТÐĺ
    -0.28
    DMI
    -0.28
    ÙĪبا
    -0.28
    IDI
    -0.27
    POSITIVE LOGITS
     manual
    0.31
    erset
    0.29
     Manual
    0.29
     pts
    0.28
     lens
    0.28
    nt
    0.27
    ffects
    0.27
     unused
    0.26
     Execution
    0.26
    _lens
    0.25
    Activations Density 74.836%

    No Known Activations