© 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. 12-TRANSCODER-HP
    7. 22414
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itr
    -0.28
    ÑĢÑıд
    -0.25
     setAddress
    -0.25
    ikt
    -0.25
    reet
    -0.24
    çī¹çĤ¹æĺ¯
    -0.24
    cap
    -0.24
     Lug
    -0.23
    odem
    -0.23
     chops
    -0.23
    POSITIVE LOGITS
    anner
    0.29
    pants
    0.28
     Computing
    0.28
    æĥ¯
    0.26
     Observer
    0.25
    æĬ½åĩº
    0.25
    æ·±åĪĩ
    0.24
    æĬ½
    0.24
    learning
    0.24
     Racing
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.