© 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. 9-TRANSCODER-HP
    7. 29864
    Prev
    Next
    INDEX
    Explanations

    fertil

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    迹
    -0.29
     disb
    -0.28
    cape
    -0.26
    踪
    -0.26
    PATCH
    -0.25
     patches
    -0.25
     cli
    -0.25
     track
    -0.24
    лаÑĤ
    -0.24
     scars
    -0.24
    POSITIVE LOGITS
    æĴ¬
    0.29
    èIJ½ä¸ĭ
    0.26
    -community
    0.26
    àªĪ
    0.26
     Guinness
    0.25
    ç®Ģæĺĵ
    0.25
    ców
    0.25
    -inverse
    0.25
    失败
    0.24
    æĭ¯
    0.24
    Activations Density 0.925%

    No Known Activations