© 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. 141393
    Prev
    Next
    INDEX
    Explanations

    Place names

    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
    ikel
    -0.28
    .metamodel
    -0.28
     lÆ°u
    -0.25
    aton
    -0.25
    itos
    -0.24
    casting
    -0.24
    èİŀ
    -0.24
    çĥĻ
    -0.23
    -than
    -0.23
    national
    -0.23
    POSITIVE LOGITS
    wers
    0.28
     verso
    0.27
    Abb
    0.26
    åħ·ä½ĵåĨħ容
    0.26
    åĢĻéĢī
    0.25
     towards
    0.25
     Abb
    0.24
    ç¡IJ
    0.24
    æľ¬æľŁ
    0.23
     toward
    0.23
    Activations Density 25.314%

    No Known Activations