© 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. 89361
    Prev
    Next
    INDEX
    Explanations

    DNA replication and chromosomes

    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
    quan
    -0.26
     lname
    -0.25
    ÑĢод
    -0.24
    Terminal
    -0.23
    ONG
    -0.23
    lug
    -0.23
    راÙĥ
    -0.23
    iden
    -0.23
    æ¸ħæ¥ļ
    -0.23
    èĬ©
    -0.23
    POSITIVE LOGITS
    çķ¥æľī
    0.34
    åģ¶å°Ķ
    0.31
    rowse
    0.26
    ä¸įèĩ³äºİ
    0.26
    itori
    0.25
    èļĢ
    0.24
    persistent
    0.24
    chos
    0.24
    rowable
    0.24
    itti
    0.24
    Activations Density 8.200%

    No Known Activations