© 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. 20-TRANSCODER-HP
    7. 63590
    Prev
    Next
    INDEX
    Explanations

    seem

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    opoulos
    -0.29
    essian
    -0.28
    als
    -0.27
     shalt
    -0.26
     closure
    -0.25
    olders
    -0.25
    æıī
    -0.25
     conclude
    -0.24
    alog
    -0.24
    _FC
    -0.24
    POSITIVE LOGITS
    eco
    0.27
    cox
    0.26
    ony
    0.25
     competit
    0.24
    icina
    0.24
    trap
    0.24
    åıĪèĥ½
    0.24
     ries
    0.24
    ëĵ¬
    0.24
     Ah
    0.23
    Activations Density 22.657%

    No Known Activations