© 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. 18-TRANSCODER-HP
    7. 89365
    Prev
    Next
    INDEX
    Explanations

    research and examination

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è´§çī©
    -0.26
    tero
    -0.26
    å¤ļ次
    -0.26
    æĬ¬å¤´
    -0.26
    umber
    -0.26
     Nack
    -0.25
     NIL
    -0.25
    æ¯Ķçī¹
    -0.25
    icut
    -0.24
    åĪº
    -0.24
    POSITIVE LOGITS
    éĿ©
    0.27
    entar
    0.26
    .ApplyResources
    0.25
     imposed
    0.25
    Ø«Ùħ
    0.24
    оÑģÑĮ
    0.24
    æī«ä¸Ģ
    0.24
    .setFocus
    0.24
    agal
    0.24
    JNI
    0.23
    Activations Density 4.412%

    No Known Activations