© 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. 14-TRANSCODER-HP
    7. 41536
    Prev
    Next
    INDEX
    Explanations

    easily

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ichten
    -0.32
     somewhere
    -0.27
    ç¬Ķ
    -0.26
    egrate
    -0.25
    æ¯Ķè¾ĥå¤ļ
    -0.24
    çĪĨ
    -0.24
    缺åı£
    -0.24
    åı¤ä»Ĭ
    -0.24
     GetComponent
    -0.24
    urette
    -0.24
    POSITIVE LOGITS
    tim
    0.27
     tim
    0.27
    çĶ¸
    0.27
    é²Ľ
    0.25
    aos
    0.25
     lac
    0.25
    ARB
    0.24
    â»ĺ
    0.24
    timer
    0.24
     real
    0.24
    Activations Density 0.349%

    No Known Activations