© 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. 39814
    Prev
    Next
    INDEX
    Explanations

    code, configuration settings

    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
    razil
    -0.30
    inverse
    -0.28
    sense
    -0.25
     airs
    -0.25
    å¹´å¼Ģå§ĭ
    -0.24
    oire
    -0.23
    AdapterFactory
    -0.23
    .Cap
    -0.23
    gaard
    -0.23
    移åĪ°
    -0.23
    POSITIVE LOGITS
    æĹº
    0.32
     pa
    0.29
    çIJĨ
    0.29
    isi
    0.27
    fi
    0.26
     diss
    0.26
    efs
    0.26
    å¹²é¢Ħ
    0.26
    身æĿIJ
    0.25
    ê¸ī
    0.25
    Activations Density 0.673%

    No Known Activations