© 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. 88566
    Prev
    Next
    INDEX
    Explanations

    form

    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
     Commonwealth
    -0.26
    ense
    -0.25
    _mob
    -0.25
    own
    -0.25
    OWN
    -0.25
    åįĥåħĥ
    -0.24
    主管éĥ¨éŨ
    -0.24
    æīĺ
    -0.24
    容æĺĵ
    -0.24
    èĩªå·±çļĦ
    -0.23
    POSITIVE LOGITS
    OfClass
    0.27
     mart
    0.26
    ä¸įåIJĥ
    0.25
    ä¸Ģåij³
    0.25
    éģĴ
    0.25
    å©Ĩ
    0.24
    alysis
    0.24
    levator
    0.24
    饴
    0.23
    rica
    0.23
    Activations Density 0.012%

    No Known Activations