© 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. 112023
    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
    izr
    -0.26
    vac
    -0.25
    vak
    -0.25
    åĽ¹
    -0.24
     cầm
    -0.24
    allee
    -0.24
    æĪijèĥ½
    -0.24
    åĩī
    -0.23
    aved
    -0.23
    nze
    -0.23
    POSITIVE LOGITS
    lux
    0.25
    廿
    0.25
    _eff
    0.25
    æľĿ
    0.25
    æŀģ
    0.25
    wards
    0.24
    ffect
    0.23
    为ä¹ĭ
    0.23
     bible
    0.23
    æŀģ为
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.