© 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. 5875
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ue
    -0.29
    æı¡
    -0.28
    ues
    -0.28
    æ¸ħ
    -0.27
    æĸĻ
    -0.25
    èĤī
    -0.25
    ç¥ĸ
    -0.25
    eur
    -0.24
    åľ°
    -0.24
    uez
    -0.24
    POSITIVE LOGITS
    cps
    0.26
    faction
    0.25
    ilden
    0.25
    __$
    0.25
    .mods
    0.24
    jad
    0.24
    æĹ¥çĶµ
    0.24
     каÑĤалог
    0.24
    åĬĽè¿ĺæĺ¯
    0.24
    xda
    0.24
    Activations Density 0.073%

    No Known Activations

    This feature has no known activations.