© 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. 5239
    Prev
    Next
    INDEX
    Explanations

    the

    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
    iph
    -0.28
    åı£ç¢ij
    -0.27
    ada
    -0.27
    ersive
    -0.26
     interaction
    -0.25
     reaching
    -0.25
     usher
    -0.25
     stranger
    -0.25
    è¾¾
    -0.24
    nels
    -0.24
    POSITIVE LOGITS
    åıĹå½±åĵį
    0.36
    åİŁæłĩé¢ĺ
    0.28
    åıĹåĪ°å½±åĵį
    0.27
    禽
    0.27
     zwiÄħz
    0.26
    slashes
    0.26
    æ£ķèī²
    0.26
    æľīèī²éĩijå±ŀ
    0.26
    uin
    0.26
     paris
    0.26
    Activations Density 0.230%

    No Known Activations