© 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. 87904
    Prev
    Next
    INDEX
    Explanations

    Religions

    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
     kra
    -0.28
    atoria
    -0.26
    æ¼¾
    -0.26
    åĬ³åĬ¨èĢħ
    -0.24
    iÄĩ
    -0.24
    enha
    -0.24
    isters
    -0.24
    -legged
    -0.24
    ed
    -0.24
     nou
    -0.24
    POSITIVE LOGITS
    å´Ħ
    0.25
    å¼¹
    0.24
    åĨ¶çĤ¼
    0.24
    agna
    0.24
    ssc
    0.24
     gras
    0.24
    ôi
    0.23
    smith
    0.23
    æŬ
    0.23
    åıĹ欢è¿İ
    0.23
    Activations Density 0.019%

    No Known Activations