© 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. 23-TRANSCODER-HP
    7. 162213
    Prev
    Next
    INDEX
    Explanations

    long form texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imentos
    -0.28
    æį¢æĪIJ
    -0.27
    iou
    -0.27
    odb
    -0.27
    ockey
    -0.26
    inin
    -0.26
       ↵↵
    -0.25
    theid
    -0.25
    æĹ¶è¾°
    -0.25
    INATION
    -0.25
    POSITIVE LOGITS
    åħ¶ä¸ŃåĮħæĭ¬
    0.28
     eins
    0.27
    åıĤä¸İåĪ°
    0.27
    çĶļ
    0.26
    åķĨ
    0.25
     belonging
    0.24
    åıĤä¸İ
    0.24
    ä¿®çIJĨ
    0.24
    çŃĶæ¡Ī
    0.24
    DataProvider
    0.24
    Activations Density 0.001%

    No Known Activations