© 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. 30-TRANSCODER-HP
    7. 96582
    Prev
    Next
    INDEX
    Explanations

    mechanics and dynamics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĩ
    -0.28
    roys
    -0.27
     двоÑĢ
    -0.26
    å¾Īé«ĺ
    -0.25
    olib
    -0.24
    åįļä¼ļ
    -0.24
    ä¸įåĩĨ
    -0.24
     Opr
    -0.24
    ürger
    -0.24
    åģ¶
    -0.23
    POSITIVE LOGITS
     mechanics
    0.33
    ynamics
    0.31
     Mechanics
    0.31
     dynamics
    0.30
    å¥Ĺè£ħ
    0.28
    å¸Ķ
    0.27
    traits
    0.27
     Dynamics
    0.27
    &P
    0.27
    Traits
    0.26
    Activations Density 0.103%

    No Known Activations