© 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. 20-TRANSCODER-HP
    7. 129677
    Prev
    Next
    INDEX
    Explanations

    Mixed data types, references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    缸çĪ±
    -0.26
    å¸Ľ
    -0.26
    apiro
    -0.25
    .truth
    -0.25
    èĢķ
    -0.24
    éĥ¨åĪĨåĨħ容
    -0.24
    éĥ¨åĪĨ
    -0.24
    apel
    -0.24
    æī©
    -0.24
    .arange
    -0.24
    POSITIVE LOGITS
    egot
    0.27
    egl
    0.26
     slightly
    0.26
    åķģ
    0.25
     Dal
    0.25
    鸵
    0.24
    ABOUT
    0.24
    ose
    0.24
    aturated
    0.24
    |č↵
    0.24
    Activations Density 2.096%

    No Known Activations