© 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. 112308
    Prev
    Next
    INDEX
    Explanations

    Code and licensing

    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
    izr
    -0.28
    ResourceManager
    -0.27
    ä¸įè§ģ
    -0.27
    ing
    -0.26
    ä¸įå±ŀäºİ
    -0.25
    INGLE
    -0.25
    afety
    -0.24
    çĿĢæīĭ
    -0.24
    çĿĢ
    -0.24
    åıijå±ķä¸Ń
    -0.24
    POSITIVE LOGITS
     modification
    0.27
     defeated
    0.27
    Modification
    0.26
    clin
    0.25
     Modify
    0.24
     modifications
    0.24
     Modification
    0.24
     Medi
    0.24
    éĥ½å¸Ĥ
    0.24
     histogram
    0.23
    Activations Density 0.001%

    No Known Activations