© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 4-TRANSCODER-HP
    7. 314
    Prev
    Next
    INDEX
    Explanations

    geometric

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    propri
    -0.26
    meric
    -0.26
    arah
    -0.25
    ↵↵
    -0.25
    çĶ²éĨĽ
    -0.24
    è§ĤæľĽ
    -0.24
    \\/
    -0.24
    AWN
    -0.23
     Burb
    -0.23
    appy
    -0.23
    POSITIVE LOGITS
    ÑģÑı
    0.28
    verbs
    0.26
    å¤©åĽ½
    0.24
    atio
    0.23
     span
    0.23
     bc
    0.23
    åľ¨è¿ĩåİ»
    0.23
    edList
    0.23
     Sco
    0.23
    åģļ
    0.23
    Activations Density 0.052%

    No Known Activations