© 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. 89423
    Prev
    Next
    INDEX
    Explanations

    Technical Q\&A

    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
     Springfield
    -0.30
    åĵĢ
    -0.29
    glomer
    -0.28
    udeau
    -0.27
    Theory
    -0.26
     Honour
    -0.26
    sweet
    -0.25
    äºĶä¸Ģ
    -0.25
    Memo
    -0.24
    -slide
    -0.24
    POSITIVE LOGITS
    wig
    0.32
    YST
    0.27
    æijĬ
    0.25
    QS
    0.25
    çij±
    0.25
    hör
    0.24
    elt
    0.24
    heiten
    0.24
    еÑģÑĤв
    0.24
    éłħ
    0.24
    Activations Density 42.849%

    No Known Activations