© 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. 20-TRANSCODER-HP
    7. 130190
    Prev
    Next
    INDEX
    Explanations

    Code and special characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç¼Ķ
    -0.27
     Editorial
    -0.27
    @email
    -0.26
     Kund
    -0.26
    conti
    -0.25
    =User
    -0.25
    ÑħваÑĤ
    -0.23
     Listed
    -0.23
    brew
    -0.23
    ayan
    -0.23
    POSITIVE LOGITS
    iated
    0.29
    æĪIJçĨŁçļĦ
    0.28
    Ãłn
    0.27
     spoiler
    0.27
    ices
    0.27
    æĿ¾
    0.27
    _fl
    0.26
     thân
    0.26
    /fl
    0.26
     flu
    0.26
    Activations Density 4.555%

    No Known Activations