© 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. 53377
    Prev
    Next
    INDEX
    Explanations

    scientific and technical writing

    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
    温
    -0.30
    溫
    -0.29
    _temp
    -0.27
    yr
    -0.27
    mont
    -0.27
    Tem
    -0.27
     Temple
    -0.27
     temp
    -0.26
    幸
    -0.26
     tem
    -0.26
    POSITIVE LOGITS
     gas
    0.26
     ::↵
    0.26
     acidic
    0.25
     de
    0.25
     Ideal
    0.24
    eners
    0.24
     ++↵
    0.24
    anj
    0.24
    ((&
    0.24
    Äĥng
    0.24
    Activations Density 0.002%

    No Known Activations