© 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. 33-TRANSCODER-HP
    7. 53860
    Prev
    Next
    INDEX
    Explanations

    Code/system text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etz
    -0.32
    åij¢
    -0.26
    æ¶ĪåĮĸ
    -0.26
    çݯå¢ĥ
    -0.24
    åįĸ
    -0.24
    -0.24
    éĩįè¦ģçļĦ
    -0.23
    çĥŃçĥĪ
    -0.23
    ÃĵN
    -0.23
    å¼Ģå±ķ
    -0.23
    POSITIVE LOGITS
    âĢ
    0.63
    ãĢĢ
    0.35
    éħįåIJĪ
    0.32
     âĢ«
    0.30
    éľİ
    0.28
    ÂŃing
    0.27
    PropertyDescriptor
    0.27
    ãĢĢãĢĢ
    0.26
    @end
    0.26
    积æŀģéħįåIJĪ
    0.26
    Activations Density 0.026%

    No Known Activations