© 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. 4752
    Prev
    Next
    INDEX
    Explanations

    Rights

    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
    çĮ«
    -0.28
    xCC
    -0.27
    å°¾
    -0.26
    sets
    -0.26
    ç»ĦåIJĪ
    -0.25
    åĵįåºĶ
    -0.25
    èĻ¹
    -0.25
     dime
    -0.25
    commended
    -0.25
    mp
    -0.25
    POSITIVE LOGITS
     Memorial
    0.30
    çĶļä¹Ī
    0.28
     whats
    0.27
    enate
    0.26
    è¿ĻçĤ¹
    0.26
    ivate
    0.26
     rust
    0.25
    ç¡Į
    0.24
    æĭ¿åĩº
    0.24
    ä¸Ģè¾ĪåŃIJ
    0.24
    Activations Density 0.046%

    No Known Activations