© 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. 88689
    Prev
    Next
    INDEX
    Explanations

    Technical writing

    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
    稼
    -0.27
    ureka
    -0.25
    ppy
    -0.25
    éĻ¶çĵ·
    -0.24
     exploits
    -0.24
    æĶ¹æĪIJ
    -0.24
    éħįåIJĪ
    -0.24
    tit
    -0.24
    ç½²
    -0.24
    oko
    -0.23
    POSITIVE LOGITS
    ä¸įæ¸ħ
    0.28
    ($__
    0.26
    幺
    0.25
    忽çķ¥äºĨ
    0.24
     reception
    0.24
    tracts
    0.24
     Vera
    0.24
    enderror
    0.24
    çīµ
    0.24
    Still
    0.24
    Activations Density 29.563%

    No Known Activations