© 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. 27-TRANSCODER-HP
    7. 8660
    Prev
    Next
    INDEX
    Explanations

    Comparing data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vore
    -0.28
     lucr
    -0.26
    缸æ¯Ķ
    -0.25
     primitive
    -0.24
     prim
    -0.24
    ussed
    -0.24
    elib
    -0.24
    xab
    -0.23
    alle
    -0.23
     garg
    -0.23
    POSITIVE LOGITS
    æĿ¥æī¾
    0.28
    åĪ¶éĢł
    0.26
     standoff
    0.26
    èĢ¸
    0.25
     straw
    0.24
    æķijåij½
    0.24
     coatings
    0.24
    ä¸Ģå®ļçļĦ
    0.23
    emble
    0.23
     spread
    0.23
    Activations Density 0.001%

    No Known Activations