© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 109541
    Prev
    Next
    INDEX
    Explanations

    Informational or conversational text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æĪij们ä¼ļ
    -0.34
    æĪij们å°Ĩ
    -0.30
    ä¼ļåľ¨
    -0.29
     guar
    -0.26
    isas
    -0.26
    åħ¬åı¸å°Ĩ
    -0.26
    æķĻæĿIJ
    -0.25
    letic
    -0.25
     Guar
    -0.25
    /WebAPI
    -0.24
    POSITIVE LOGITS
    éĺµéĺµ
    0.29
    计åĪĴ
    0.26
    河边
    0.26
     Ment
    0.25
    辨
    0.25
    ROLS
    0.24
    å·²ä¹ħçļĦ
    0.24
    ì¸
    0.24
    åĪ¶å®ļ
    0.24
    çĶ¨æīĭ
    0.23
    Activations Density 0.928%

    No Known Activations