© 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. 88573
    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
    -che
    -0.25
    SETTING
    -0.25
    -basket
    -0.24
    çļĦè¦ģæ±Ĥ
    -0.24
    Violation
    -0.24
    èĽĭ
    -0.24
    -env
    -0.23
    Later
    -0.23
     воз
    -0.23
    later
    -0.23
    POSITIVE LOGITS
    æĭ´
    0.28
    åºĶæĶ¶
    0.28
     sup
    0.26
    orks
    0.25
     tend
    0.25
    ç§ķ
    0.25
     ci
    0.25
    upy
    0.24
    æݥ触
    0.24
    erve
    0.24
    Activations Density 0.005%

    No Known Activations

    This feature has no known activations.