© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 4-TRANSCODER-HP
    7. 7
    Prev
    Next
    INDEX
    Explanations

    LR

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĩºåľº
    -0.31
     refere
    -0.29
    å±ĢéĿ¢
    -0.28
    åĽłåľ°åĪ¶å®ľ
    -0.28
    éĿł
    -0.27
    HUD
    -0.26
    mat
    -0.26
     diz
    -0.25
    UserRole
    -0.25
     OT
    -0.25
    POSITIVE LOGITS
    ACY
    0.28
    第åįģ
    0.26
    ponent
    0.26
    éªĪ
    0.26
    第ä¸ĥ
    0.26
    phans
    0.25
    æľĢå°ij
    0.25
    AGMA
    0.24
    .utf
    0.24
    èħ¹
    0.24
    Activations Density 0.058%

    No Known Activations