© 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. 12-TRANSCODER-HP
    7. 23560
    Prev
    Next
    INDEX
    Explanations

    hydrocarbons and hydrogenation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è··
    -0.29
    dig
    -0.26
    type
    -0.26
    éĽĢ
    -0.26
    EObject
    -0.26
    classpath
    -0.25
    promise
    -0.25
    íĮ½
    -0.24
    mix
    -0.24
    ä¸ĢéĹª
    -0.24
    POSITIVE LOGITS
     starts
    0.26
    æŁł
    0.24
    rema
    0.24
    æģŃ
    0.24
     begins
    0.24
    çĽĺ
    0.24
    å°¼äºļ
    0.24
    éĢĨè¢Ń
    0.23
     Initialise
    0.23
    odon
    0.23
    Activations Density 0.001%

    No Known Activations