© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 14-TRANSCODER-HP
    7. 40313
    Prev
    Next
    INDEX
    Explanations

    varied text sources

    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
    Not in Any Lists

    No Comments

    Negative Logits
     theirs
    -0.30
    å°ıåŃIJ
    -0.27
     '<?
    -0.26
    ozo
    -0.25
    ä¸Ģéĥ¨
    -0.25
    产åĢ¼
    -0.25
    ocking
    -0.24
    chez
    -0.24
    rox
    -0.24
    åĬŀ好
    -0.24
    POSITIVE LOGITS
    éĢĤæŶ
    0.28
    åĪĴåĪĨ
    0.26
     transit
    0.25
    èģĶ
    0.25
     configure
    0.25
    еÑĩен
    0.25
     accept
    0.25
    ãģĭãģ¤
    0.25
    çIJĨå·¥
    0.24
    abella
    0.24
    Activations Density 0.205%

    No Known Activations