© 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. 9-TRANSCODER-HP
    7. 29750
    Prev
    Next
    INDEX
    Explanations

    Noisy text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adian
    -0.26
     octave
    -0.25
    å½¢
    -0.25
    è¾IJ
    -0.24
     reflecting
    -0.24
     Imports
    -0.24
    antis
    -0.24
     imports
    -0.24
     scalp
    -0.24
     rug
    -0.24
    POSITIVE LOGITS
    åĩºè·¯
    0.27
     Dise
    0.26
    Streams
    0.26
    缴åįĩ
    0.26
    èĮĤ
    0.25
    èµĸ以
    0.25
    _streams
    0.25
    æį¢åıĸ
    0.24
     turb
    0.24
    sat
    0.24
    Activations Density 0.105%

    No Known Activations