© 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. 5350
    Prev
    Next
    INDEX
    Explanations

    truth

    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
     eens
    -0.23
    ±
    -0.23
     resto
    -0.23
    lass
    -0.22
    让她
    -0.22
     Hatch
    -0.22
    bbing
    -0.22
    ä¸ĵ人
    -0.21
    :///
    -0.21
     público
    -0.21
    POSITIVE LOGITS
    fully
    0.31
    istic
    0.30
    ful
    0.28
    ä»ĬçĶŁ
    0.28
    主ä¹īæĢĿæĥ³
    0.28
    heets
    0.26
    åŃ°
    0.25
    heet
    0.25
    omm
    0.25
    -hearted
    0.25
    Activations Density 0.462%

    No Known Activations