© 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. 22981
    Prev
    Next
    INDEX
    Explanations

    energy

    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
     ca
    -0.29
    (ca
    -0.26
    æ´¼
    -0.26
    -ca
    -0.25
    styl
    -0.25
    .uml
    -0.25
    饲
    -0.24
    åħ³
    -0.24
    TPL
    -0.24
    ccount
    -0.24
    POSITIVE LOGITS
    çĴľ
    0.28
     diversified
    0.27
     blanket
    0.26
    agedList
    0.25
    lung
    0.25
     suited
    0.24
     Collective
    0.24
    æĿ¾å¼Ľ
    0.24
    ollect
    0.23
     belonged
    0.23
    Activations Density 0.004%

    No Known Activations