© 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. 8938
    Prev
    Next
    INDEX
    Explanations

    center

    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
    åĪĽä¸ļèĢħ
    -0.28
    fade
    -0.27
    çļĦèµĦéĩij
    -0.26
    uvw
    -0.26
    åľ¨æĪij
    -0.25
    ksi
    -0.25
    COPE
    -0.25
    éĻ£
    -0.24
    åľ¨åħ¶
    -0.24
    ÙħØ©
    -0.24
    POSITIVE LOGITS
    ood
    0.29
    iagnostics
    0.27
    ing
    0.26
    é³ŀ
    0.26
    ENCES
    0.26
    磶
    0.26
    ents
    0.26
    wo
    0.26
     Ankara
    0.25
    imiter
    0.25
    Activations Density 0.004%

    No Known Activations