© 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. 97494
    Prev
    Next
    INDEX
    Explanations

    .

    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
    masters
    -0.29
    设æľī
    -0.27
    请æĤ¨
    -0.26
    è¡·å¿ĥ
    -0.26
    å®ļéĩı
    -0.25
     adore
    -0.24
     FX
    -0.24
    TO
    -0.24
    åĮª
    -0.24
     createAction
    -0.23
    POSITIVE LOGITS
    å½ĵçĦ¶
    0.27
    ãģłãģĮ
    0.27
     even
    0.27
     human
    0.25
    bench
    0.25
    ì§Ģë§Į
    0.25
     ÙĦÙĥÙĨ
    0.24
    @dynamic
    0.24
     exagger
    0.23
    ¿
    0.23
    Activations Density 0.005%

    No Known Activations