© 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. 14-TRANSCODER-HP
    7. 40009
    Prev
    Next
    INDEX
    Explanations

    answering religious questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    丢
    -0.25
     Sovere
    -0.25
     Right
    -0.24
    _SENT
    -0.23
     Cave
    -0.23
    å½ĵä»Ĭ
    -0.23
    èĦī
    -0.23
    æŶæķĪ
    -0.23
    æľ
    -0.22
     Spare
    -0.22
    POSITIVE LOGITS
    PJ
    0.28
    esses
    0.28
     PJ
    0.28
     topping
    0.25
    IRQ
    0.24
    adf
    0.24
     refill
    0.24
    IR
    0.24
     para
    0.24
     &,
    0.24
    Activations Density 0.162%

    No Known Activations