© 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. 129943
    Prev
    Next
    INDEX
    Explanations

    locations and weather

    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
     statically
    -0.24
    è®·
    -0.24
     Buster
    -0.24
    éĻ¤
    -0.23
     competence
    -0.23
    nj
    -0.23
    Pure
    -0.23
     Monkey
    -0.23
    èļĵ
    -0.22
    ÑģоÑģ
    -0.22
    POSITIVE LOGITS
    æIJŃ
    0.32
    æ°¸è¿ľ
    0.29
    端æŃ£
    0.27
    obel
    0.27
    onian
    0.26
    asher
    0.25
    ä»·
    0.24
    çĪ±å°Ķ
    0.24
    åľ¨åħ¶
    0.24
    ogr
    0.24
    Activations Density 10.433%

    No Known Activations