© 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. 40735
    Prev
    Next
    INDEX
    Explanations

    toys and games

    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
    -fashion
    -0.28
    å¾Ĺ好
    -0.26
    iteur
    -0.25
    .appspot
    -0.25
     subjects
    -0.25
    ä¸ĢåĪĢ
    -0.25
    _ABI
    -0.24
    .removeItem
    -0.24
    _scope
    -0.24
    ering
    -0.24
    POSITIVE LOGITS
    åĥµ
    0.31
    adh
    0.29
    çī¹æ®Ĭ
    0.29
     care
    0.28
    çħ§
    0.26
    æĥ°
    0.26
    é«ĺé¢ij
    0.25
    çī¹æ®ĬçļĦ
    0.25
    éĿł
    0.25
     ass
    0.25
    Activations Density 0.059%

    No Known Activations