© 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
    2. Qwen3-4B
    3. 14-TRANSCODER-HP
    4. 40964
    Prev
    Next
    INDEX
    Explanations

    classifications and categorizations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lite
    -0.28
    nga
    -0.27
     示
    -0.26
    got
    -0.25
    slow
    -0.24
    çįł
    -0.24
    èŀºæĹĭ
    -0.24
     ÐłÑĥÑģ
    -0.23
    .percent
    -0.23
    .LoggerFactory
    -0.23
    POSITIVE LOGITS
    idable
    0.29
    说çļĦæĺ¯
    0.27
    ording
    0.27
    oded
    0.27
    atable
    0.26
    odes
    0.26
    wald
    0.25
    çĬĢ
    0.25
    oder
    0.25
    åĵī
    0.25
    Activations Density 0.296%

    No Known Activations