© 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. 19-TRANSCODER-HP
    7. 8337
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸Ńå¿ĥåŁİå¸Ĥ
    -0.27
    noinspection
    -0.26
    æķĻè®Ń
    -0.26
    人å¿ĥ
    -0.25
     costs
    -0.25
    讫
    -0.25
    éľĩæħij
    -0.25
    nid
    -0.25
    对éĿ¢
    -0.24
    æ¢ħèĬ±
    -0.24
    POSITIVE LOGITS
     [...]
    0.27
    chants
    0.27
    Controllers
    0.26
    ally
    0.25
     unint
    0.25
    DownList
    0.24
     [âĢ¦]
    0.24
    getStore
    0.24
     ölçü
    0.24
    ":""
    0.23
    Activations Density 0.081%

    No Known Activations

    This feature has no known activations.