© 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. 32-TRANSCODER-HP
    7. 42070
    Prev
    Next
    INDEX
    Explanations

    air

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Carry
    -0.30
    HeaderValue
    -0.30
    bu
    -0.29
     equilibrium
    -0.29
    åĪ©
    -0.27
    dam
    -0.25
     Cross
    -0.25
    mmo
    -0.25
    ella
    -0.25
    opy
    -0.24
    POSITIVE LOGITS
     air
    0.58
    空æ°Ķ
    0.48
    Air
    0.43
    air
    0.42
    -air
    0.41
    _air
    0.40
     Air
    0.39
    为空
    0.37
    .air
    0.36
    airs
    0.35
    Activations Density 0.002%

    No Known Activations