© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 18-TRANSCODER-HP
    7. 89971
    Prev
    Next
    INDEX
    Explanations

    code snippets/technical language

    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
    //{{
    -0.26
     endian
    -0.26
    reopen
    -0.25
    etty
    -0.24
    ධ
    -0.24
     complimentary
    -0.24
     (.
    -0.24
     details
    -0.24
    详ç»ĨçļĦ
    -0.23
     parcels
    -0.23
    POSITIVE LOGITS
    产åĵģè´¨éĩı
    0.31
    æŀģéĻIJ
    0.27
    æī¹éĩı
    0.26
     versus
    0.26
    moth
    0.26
    æľĢ大éĻIJ度
    0.26
    -vers
    0.26
    å¼¹
    0.26
    -vs
    0.26
    Äŀ
    0.26
    Activations Density 6.873%

    No Known Activations