© 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. 98335
    Prev
    Next
    INDEX
    Explanations

    Medical prefixes (hypo, op)

    np_max-act · gemini-2.0-flash
    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
     Acts
    -0.31
     designer
    -0.25
    onor
    -0.25
    ãģ¤ãģĭ
    -0.24
    糣
    -0.24
    æĶ¹éĿ©åıijå±ķ
    -0.24
    inary
    -0.23
    ired
    -0.23
     actu
    -0.23
    thy
    -0.23
    POSITIVE LOGITS
    çļĦä¸ĢåĪĩ
    0.27
    æ¯Ľ
    0.24
    åĶ§
    0.24
    àºĩ
    0.24
    	tests
    0.24
    ?p
    0.24
    rieg
    0.24
    .getExternalStorage
    0.23
    plies
    0.23
    è¿Ļä¸Ģ次
    0.22
    Activations Density 0.027%

    No Known Activations