© 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. 111905
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    uder
    -0.28
    _CRITICAL
    -0.26
    fel
    -0.24
    æĻĤãģ¯
    -0.23
    peare
    -0.23
    atem
    -0.23
    è°ĥä¾ĥ
    -0.23
     strt
    -0.23
    ristol
    -0.23
    lda
    -0.22
    POSITIVE LOGITS
    monic
    0.28
    emony
    0.27
    为主
    0.26
    on
    0.26
    igrant
    0.25
    é£İåij³
    0.25
     powered
    0.24
     procedures
    0.24
     networks
    0.24
    igned
    0.23
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.