© 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. 5033
    Prev
    Next
    INDEX
    Explanations

    when/if

    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
    aben
    -0.32
    æĺİ
    -0.28
    abra
    -0.28
    åŃľ
    -0.25
    ÑŁ
    -0.25
    ç©·
    -0.24
    çļĦç»ĵæŀľ
    -0.24
    麹
    -0.24
     ainsi
    -0.24
    åĪ»çĶ»
    -0.24
    POSITIVE LOGITS
    æĪĸ许
    0.28
    esimal
    0.25
     uncertain
    0.25
     Blade
    0.24
    oral
    0.24
    orman
    0.24
     silently
    0.24
     tips
    0.23
    ritch
    0.23
     lands
    0.23
    Activations Density 0.087%

    No Known Activations