© 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. 97789
    Prev
    Next
    INDEX
    Explanations

    References

    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
    icted
    -0.28
     nexus
    -0.24
    æĤ´
    -0.24
    á»ĵ
    -0.23
    /fonts
    -0.23
     Guinness
    -0.23
     Pron
    -0.23
     plat
    -0.23
    ocrat
    -0.23
     Nir
    -0.22
    POSITIVE LOGITS
    ìĭ¤
    0.29
     poc
    0.28
     abstract
    0.27
    EST
    0.27
    OO
    0.27
    éŀĺ
    0.26
    ìĭ
    0.26
    antas
    0.25
    Abstract
    0.25
     Rou
    0.25
    Activations Density 0.007%

    No Known Activations