© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7488
    Prev
    Next
    INDEX
    Explanations

    systems, devices, reviews, ownership

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ring
    -0.29
    -stop
    -0.26
    ä¸Ģç±»
    -0.26
    ä¸Ģè¾¹
    -0.25
     rings
    -0.25
     travel
    -0.25
     stops
    -0.24
    ÙĬبة
    -0.24
    "".
    -0.24
    ability
    -0.24
    POSITIVE LOGITS
    ianne
    0.27
     luckily
    0.25
    éĶ¤
    0.24
    icum
    0.24
    ä¸ĵä¸ļçļĦ
    0.24
    voke
    0.23
    tero
    0.23
     trainer
    0.23
    atus
    0.23
    ntl
    0.23
    Activations Density 1.065%

    No Known Activations