© 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. 22-TRANSCODER-HP
    7. 87433
    Prev
    Next
    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uchar
    -0.27
    交æį¢
    -0.26
    uttle
    -0.25
    athed
    -0.25
     barred
    -0.24
     momentarily
    -0.24
    毫
    -0.24
    çľģ
    -0.24
     wholly
    -0.24
     meanwhile
    -0.24
    POSITIVE LOGITS
    esign
    0.30
     definition
    0.29
    definition
    0.27
    æĮĩåįĹ
    0.26
     Dag
    0.25
     Definition
    0.25
     Fame
    0.24
    ptive
    0.24
     Reviewed
    0.23
    èĬ±å¼Ģ
    0.23
    Activations Density 0.011%

    No Known Activations