© 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. 9238
    Prev
    Next
    INDEX
    Explanations

    Giants

    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
    posable
    -0.26
     reprodu
    -0.26
    èįª
    -0.25
    产åIJİ
    -0.25
    anter
    -0.25
     reproduce
    -0.25
    okit
    -0.24
     Dob
    -0.24
    é£ŀç¿Ķ
    -0.24
    oky
    -0.24
    POSITIVE LOGITS
    å¦Ĵ
    0.29
    esson
    0.26
    æĶ¾
    0.26
    å«īå¦Ĵ
    0.26
    locale
    0.26
    quil
    0.25
    ãĥ¼ãĥĹ
    0.25
    åĨĴ
    0.25
    icker
    0.25
    ep
    0.25
    Activations Density 0.878%

    No Known Activations