© 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. 27-TRANSCODER-HP
    7. 57287
    Prev
    Next
    INDEX
    Explanations

    ability/inability

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸įéĢļ
    -0.35
    enet
    -0.29
     nest
    -0.28
    èµĦ产è¯Ħä¼°
    -0.28
    รà¸ĩ
    -0.27
    Allow
    -0.26
     LOSS
    -0.25
    çĥ§
    -0.25
    çŁ¿çī©
    -0.25
    iscal
    -0.24
    POSITIVE LOGITS
    å¿ĥæĦı
    0.27
    ivities
    0.26
     Discipline
    0.26
    罪
    0.25
     âĨij
    0.25
    CardBody
    0.25
     paced
    0.24
     Plain
    0.24
     affairs
    0.24
    åīįè¿Ľ
    0.23
    Activations Density 0.005%

    No Known Activations