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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5861
    Prev
    Next
    INDEX
    Explanations

    code

    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
    带æĿ¥çļĦ
    -0.28
    .bn
    -0.25
    éĥ½èĥ½å¤Ł
    -0.24
    .TextAlignment
    -0.24
    éĢĢ
    -0.24
    utm
    -0.24
    SENS
    -0.24
    phabet
    -0.24
    .cg
    -0.24
    utow
    -0.24
    POSITIVE LOGITS
    åĩłåĪĨ
    0.26
    çĤºäºĨ
    0.25
     Officers
    0.25
    (Method
    0.25
    aryl
    0.24
    京åī§
    0.24
    (optimizer
    0.24
    ilig
    0.24
    anas
    0.24
    ilon
    0.23
    Activations Density 0.008%

    No Known Activations