© 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. 88888
    Prev
    Next
    INDEX
    Explanations

    Technical/programming documentation

    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
    IMUM
    -0.25
    è¯Ŀ
    -0.25
    zens
    -0.25
     Strength
    -0.24
     ttl
    -0.24
    pta
    -0.24
    Strength
    -0.24
    æ¼Ķ
    -0.23
     InputStreamReader
    -0.23
     screened
    -0.23
    POSITIVE LOGITS
    第äºĮç§į
    0.29
    缸åıį
    0.28
     rather
    0.27
    /Public
    0.27
    PointerType
    0.27
     ngược
    0.26
     type
    0.25
     Fol
    0.25
    å¿«æĬ¥
    0.24
    åı¦ä¸Ģç§į
    0.24
    Activations Density 32.493%

    No Known Activations