© 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. 33-TRANSCODER-HP
    7. 52940
    Prev
    Next
    INDEX
    Explanations

    References and information

    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
    Not in Any Lists

    No Comments

    Negative Logits
     hol
    -0.32
    æľ¬ç½ijç«Ļ
    -0.28
    çŃ¹
    -0.28
    æł¼
    -0.27
    ç´
    -0.27
    çĮĿ
    -0.27
    ugi
    -0.26
     Vy
    -0.26
    å®ŀä½ĵ
    -0.26
    ector
    -0.25
    POSITIVE LOGITS
    tridge
    0.27
    Thunder
    0.26
    Enumerator
    0.25
    Hunter
    0.25
     Andrews
    0.25
     Heads
    0.24
     Matching
    0.24
    亨
    0.24
    avern
    0.24
    nable
    0.24
    Activations Density 0.010%

    No Known Activations