© 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. 40725
    Prev
    Next
    INDEX
    Explanations

    Code snippets and summaries

    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
     pool
    -0.33
    -theme
    -0.26
     theme
    -0.26
    çī§
    -0.26
     pools
    -0.26
     probabilities
    -0.25
     brakes
    -0.25
     Ges
    -0.25
    èĪħ
    -0.24
    æī£
    -0.24
    POSITIVE LOGITS
     propriet
    0.28
    carbon
    0.27
    bite
    0.26
    guards
    0.26
    hart
    0.25
    èĪįå¾Ĺ
    0.24
    blade
    0.24
    scape
    0.24
    å»ĵ
    0.24
    guard
    0.24
    Activations Density 1.210%

    No Known Activations