© 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. 112508
    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
    çļĦè¯Ŀ
    -0.26
    peon
    -0.25
    ombat
    -0.25
    kür
    -0.25
    azel
    -0.24
    ORED
    -0.24
    ä¹ĭæĥħ
    -0.24
    arrera
    -0.24
    çļĦ話
    -0.24
    redict
    -0.24
    POSITIVE LOGITS
    rm
    0.28
    gm
    0.26
    und
    0.26
     reflecting
    0.25
    åĶ
    0.25
    è¯Ī
    0.25
     Reflect
    0.25
    LEM
    0.25
    éĹ®
    0.24
    ct
    0.24
    Activations Density 0.032%

    No Known Activations

    This feature has no known activations.