© 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. 19-TRANSCODER-HP
    7. 6223
    Prev
    Next
    INDEX
    Explanations

    Science and technology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     observ
    -0.29
    observ
    -0.29
     acknowled
    -0.26
    etheless
    -0.26
     mand
    -0.25
    å½
    -0.25
    egov
    -0.25
    licted
    -0.25
    elin
    -0.25
     temporarily
    -0.25
    POSITIVE LOGITS
    æŀ¶
    0.29
     cab
    0.26
    _che
    0.26
    che
    0.24
    ardy
    0.24
    yyy
    0.23
     enumerator
    0.23
    Che
    0.23
     Fortress
    0.23
     shady
    0.23
    Activations Density 0.040%

    No Known Activations