© 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. 108459
    Prev
    Next
    INDEX
    Explanations

    decision

    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
    atif
    -0.33
    udent
    -0.32
    ftar
    -0.26
    eed
    -0.26
    Leaks
    -0.24
    alent
    -0.24
    oire
    -0.24
    èѦæĥķ
    -0.24
    æį¢å±Ĭ
    -0.24
     scratching
    -0.24
    POSITIVE LOGITS
    éģĵ
    0.26
    æ°¸
    0.25
     justification
    0.25
    åı«
    0.24
     åIJį
    0.24
     sob
    0.24
    çIJĨ
    0.24
    没人
    0.24
    没æľī人
    0.24
    æĺ¯è°ģ
    0.23
    Activations Density 0.136%

    No Known Activations