© 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. 112088
    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
    bull
    -0.27
    ewise
    -0.27
    commons
    -0.25
    sworth
    -0.25
    åĢĴ
    -0.24
     enrol
    -0.24
    çĭ¬
    -0.24
    åµ´
    -0.24
    ack
    -0.24
    clid
    -0.24
    POSITIVE LOGITS
     ourselves
    0.27
     Sao
    0.27
     themselves
    0.26
     peg
    0.26
     nämlich
    0.25
     Trie
    0.24
    AGO
    0.24
     MIS
    0.24
    çĶ²
    0.23
    .boolean
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.