© 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. 22-TRANSCODER-HP
    7. 87696
    Prev
    Next
    INDEX
    Explanations

    math and software

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĹ¢çĦ¶
    -0.31
     ^.
    -0.29
    rial
    -0.26
    ]^
    -0.26
    æĹ¢æľī
    -0.26
    åħĪæĬĬ
    -0.25
    getClass
    -0.24
    aday
    -0.24
    éķĩæ±Ł
    -0.23
    éªĹåıĸ
    -0.23
    POSITIVE LOGITS
    éħĿéħ¿
    0.31
    tw
    0.29
    åĨħåľ°
    0.28
    èĮĥ
    0.28
    .tw
    0.28
     sw
    0.27
    åħ°
    0.27
    è½»è½»åľ°
    0.26
    çļĦåľ°æĸ¹
    0.26
    enter
    0.26
    Activations Density 0.001%

    No Known Activations