© 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. 89091
    Prev
    Next
    INDEX
    Explanations

    God

    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
    è¾IJ
    -0.28
    ereum
    -0.26
     impass
    -0.26
    çĨı
    -0.25
     *</
    -0.25
    idar
    -0.24
    Margin
    -0.24
     Epid
    -0.24
    osate
    -0.24
    uded
    -0.24
    POSITIVE LOGITS
    esome
    0.26
    UILT
    0.25
    大å±Ģ
    0.25
    &action
    0.25
     ``
    0.24
    çĴ°
    0.24
    NAL
    0.23
    alyze
    0.23
    æł¼
    0.23
    è´¢æĶ¿éĥ¨
    0.23
    Activations Density 6.322%

    No Known Activations