© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 4-TRANSCODER-HP
    7. 240
    Prev
    Next
    INDEX
    Explanations

    upgrade

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    &id
    -0.26
    PE
    -0.26
    ä¸Ģä¸ĭ
    -0.26
    zend
    -0.25
    åijĹ
    -0.25
    lay
    -0.25
    maintenance
    -0.25
    åħ³ç³»
    -0.25
    èĦī
    -0.25
    hexdigest
    -0.24
    POSITIVE LOGITS
    dden
    0.26
     Poss
    0.26
    è¡£
    0.25
    Toolkit
    0.25
    ¦Ĥ
    0.24
     Y
    0.24
     director
    0.24
     feared
    0.24
    	Y
    0.24
    æģIJæĢķ
    0.24
    Activations Density 0.075%

    No Known Activations