© 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. 89835
    Prev
    Next
    INDEX
    Explanations

    Past tense/history

    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
    nings
    -0.27
     stil
    -0.25
     Correction
    -0.24
    aug
    -0.24
    ducted
    -0.24
    çªĹå¸ĺ
    -0.24
    devil
    -0.23
    UDGE
    -0.23
    -den
    -0.23
     fel
    -0.23
    POSITIVE LOGITS
    ç»ŀ
    0.24
    MES
    0.24
    éĥ¦
    0.24
    éĺļ
    0.24
     braz
    0.24
     breached
    0.23
     leaking
    0.23
    пÑĢав
    0.23
     unm
    0.23
    å³
    0.23
    Activations Density 17.118%

    No Known Activations