© 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. 89389
    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
     look
    -0.30
    ulfill
    -0.29
    é«ĺæ°´å¹³
    -0.28
     remind
    -0.28
     living
    -0.28
    æıIJéĨĴ
    -0.26
    _places
    -0.26
    çĶ³
    -0.26
     place
    -0.26
    orp
    -0.26
    POSITIVE LOGITS
    åıijçĹħ
    0.26
    RIC
    0.25
    andi
    0.25
    bite
    0.25
    assin
    0.24
    dling
    0.24
    åģĥ
    0.24
    datum
    0.24
    AJOR
    0.24
     Karn
    0.23
    Activations Density 1.732%

    No Known Activations

    This feature has no known activations.