© 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. 129715
    Prev
    Next
    INDEX
    Explanations

    room

    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
     satur
    -0.28
    igators
    -0.24
    secs
    -0.24
    _ring
    -0.24
    å¤ļæł·åĮĸ
    -0.23
     vö
    -0.23
     Soc
    -0.22
    vore
    -0.22
    éħļ
    -0.22
    amation
    -0.22
    POSITIVE LOGITS
    mates
    0.33
    bed
    0.29
    spaces
    0.28
    space
    0.27
    ROOM
    0.26
    egal
    0.26
    ä¼ļ议室
    0.26
    ponses
    0.26
    åĨħçļĦ
    0.25
    outh
    0.25
    Activations Density 0.462%

    No Known Activations