© 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. 88540
    Prev
    Next
    INDEX
    Explanations

    live

    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
    _ping
    -0.28
    :convert
    -0.27
    arton
    -0.24
    æĶĺ
    -0.24
    EntryPoint
    -0.24
     Ping
    -0.24
    çĭĻ
    -0.23
    rets
    -0.23
    @(
    -0.22
    æĪIJ绩
    -0.22
    POSITIVE LOGITS
    RTC
    0.25
    insk
    0.25
    bat
    0.24
    æ°§
    0.23
    ins
    0.23
    idency
    0.23
     severity
    0.22
    ặp
    0.22
    ibri
    0.22
    itness
    0.22
    Activations Density 9.238%

    No Known Activations