© 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. 5849
    Prev
    Next
    INDEX
    Explanations

    descriptive texts

    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
     diff
    -0.32
     Diff
    -0.30
     cnt
    -0.26
    æ´¾åĩº
    -0.26
     newArr
    -0.26
     Till
    -0.26
    ç§
    -0.26
    diff
    -0.25
     swal
    -0.25
    cnt
    -0.25
    POSITIVE LOGITS
    åıijå¸ĥæŶéĹ´
    0.29
    Coordinate
    0.27
     Coordinate
    0.27
    ólica
    0.25
     allure
    0.25
     antid
    0.25
    minent
    0.25
     DefaultValue
    0.25
    è¿Ľåĩºåı£
    0.25
    ANGED
    0.24
    Activations Density 0.016%

    No Known Activations