© 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. 40689
    Prev
    Next
    INDEX
    Explanations

    logen

    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
    éħį
    -0.32
    éĻª
    -0.29
    æĪIJ
    -0.28
    åıĤåĬł
    -0.27
    ystals
    -0.26
     refl
    -0.26
     Exposure
    -0.26
     onload
    -0.26
     na
    -0.26
    éĤ£éĩĮ
    -0.26
    POSITIVE LOGITS
    antom
    0.31
    dance
    0.29
    æĬķèµĦé¡¹çĽ®
    0.28
    ceeded
    0.27
    讣
    0.27
    cede
    0.26
    moth
    0.26
    iek
    0.26
    å¹´ä¹ĭä¹ħ
    0.26
    åħ¬åı¸å°Ĩ
    0.26
    Activations Density 2.931%

    No Known Activations