© 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. 89344
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Trouble
    -0.26
    æī¹åıij
    -0.25
    ;\
    -0.24
     hätte
    -0.24
    PACK
    -0.24
     anch
    -0.24
    еÑĤе
    -0.24
    usal
    -0.23
     svenska
    -0.23
    便åĪ©
    -0.23
    POSITIVE LOGITS
    atten
    0.28
    ONUS
    0.27
    upal
    0.25
    nel
    0.25
     repet
    0.24
     even
    0.23
    metis
    0.23
    åı¯è§Ĩ
    0.23
    vary
    0.23
    iss
    0.23
    Activations Density 3.680%

    No Known Activations

    This feature has no known activations.