© 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. 25-TRANSCODER-HP
    7. 109018
    Prev
    Next
    INDEX
    Explanations

    observation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¦į
    -0.32
    Compression
    -0.27
    ARDS
    -0.26
    olicy
    -0.26
    å¦Ĩ
    -0.26
     Losing
    -0.25
    ophile
    -0.25
    âĪ½
    -0.25
    åĢºåĬ¡
    -0.25
    lust
    -0.25
    POSITIVE LOGITS
     observation
    0.29
     informed
    0.28
     observations
    0.27
    桧
    0.27
     observed
    0.27
     continua
    0.27
     observational
    0.26
    æķĪæŀľ
    0.26
    éĻĽ
    0.26
    è§Ĥå¯Ł
    0.25
    Activations Density 0.892%

    No Known Activations