© 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. 112156
    Prev
    Next
    INDEX
    Explanations

    Abbreviations and Locations

    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
    çī¹çĤ¹æĺ¯
    -0.31
    å·¥ç¨ĭæĬĢæľ¯
    -0.26
    .pp
    -0.25
    jmp
    -0.25
    #:
    -0.25
    MR
    -0.25
    çīĪ
    -0.25
    íij¸
    -0.25
    第ä¸ĢèĬĤ
    -0.25
    еÑĢж
    -0.24
    POSITIVE LOGITS
     night
    0.26
    spiracy
    0.25
    ada
    0.25
     face
    0.25
     grand
    0.24
    çĭĦ
    0.24
     unity
    0.24
    assic
    0.24
     figures
    0.24
     region
    0.23
    Activations Density 0.009%

    No Known Activations