© 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. 52692
    Prev
    Next
    INDEX
    Explanations

    h

    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
    çĵ¢
    -0.28
    éĩĩ
    -0.27
    g
    -0.27
    GINE
    -0.26
    奶
    -0.26
    è´¨
    -0.26
    åĨ³
    -0.25
    æĬ½
    -0.25
    çĽ²
    -0.25
     Ins
    -0.25
    POSITIVE LOGITS
    leases
    0.28
     sounded
    0.26
    ToOne
    0.25
    ollar
    0.25
    åIJĦè¡Į
    0.24
     em
    0.24
     Andrews
    0.24
    OUNDS
    0.24
     kin
    0.24
     ang
    0.24
    Activations Density 0.019%

    No Known Activations