© 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. 97449
    Prev
    Next
    INDEX
    Explanations

    Articles and linking verbs

    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
    -mf
    -0.28
    Msp
    -0.25
    ,cp
    -0.25
    BERS
    -0.25
    ictions
    -0.25
    çīĿ
    -0.24
     EQUAL
    -0.24
    äºį
    -0.24
    ARS
    -0.24
    _CSV
    -0.24
    POSITIVE LOGITS
    sn
    0.29
    inite
    0.29
    “
    0.28
     lower
    0.28
     GC
    0.27
     upper
    0.27
     bekannt
    0.27
     “
    0.27
     finish
    0.26
    主åĬ¨
    0.26
    Activations Density 0.007%

    No Known Activations