© 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. 130461
    Prev
    Next
    INDEX
    Explanations

    Corporation

    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
    grow
    -0.29
    hin
    -0.25
    upil
    -0.24
     Liberation
    -0.24
    jej
    -0.23
    ä¸įæĸŃåĪĽæĸ°
    -0.23
    åĽ½å®¶å®īåħ¨
    -0.23
    KV
    -0.23
    ért
    -0.23
     chiar
    -0.23
    POSITIVE LOGITS
    dera
    0.27
     miser
    0.25
    allen
    0.24
    ity
    0.23
    åºŁè¯Ŀ
    0.23
    ยาย
    0.23
    otta
    0.23
    åıĭæĥħ
    0.23
    ama
    0.22
    reflect
    0.22
    Activations Density 0.172%

    No Known Activations