© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7261
    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
    Enlarge
    -0.29
    å½ĵä¸Ń
    -0.28
    åıijå±ķ缮æłĩ
    -0.28
    tribute
    -0.25
    æ®ĭ
    -0.25
    æ®ĸ
    -0.25
     trait
    -0.25
    еÑĩ
    -0.24
     tense
    -0.24
    GeV
    -0.24
    POSITIVE LOGITS
    æĬĬæı¡
    0.27
    çľĭåĪ°äºĨ
    0.27
    æĶ¶åĪ°äºĨ
    0.26
    ÐĺÐĿ
    0.26
     tu
    0.26
    æĦŁæĤŁ
    0.26
    çĤ¹åĩ»æŁ¥çľĭ
    0.24
    ÑģлÑĥÑĪ
    0.23
    mint
    0.23
     inout
    0.23
    Activations Density 2.022%

    No Known Activations

    This feature has no known activations.