© 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. 25-TRANSCODER-HP
    7. 107441
    Prev
    Next
    INDEX
    Explanations

    technical/medical writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çĽ´çº¿
    -0.31
    ton
    -0.30
    交åıī
    -0.28
     compat
    -0.27
    tons
    -0.27
    åħ¼å®¹
    -0.26
    DOI
    -0.26
     compatible
    -0.26
     diagon
    -0.26
    åĽŃåĮº
    -0.25
    POSITIVE LOGITS
    çĪ¸å¦Ī
    0.29
    иÑĤа
    0.28
     survivors
    0.28
    vens
    0.28
    brit
    0.27
    estination
    0.26
    erox
    0.25
    æĦıèŃĺ
    0.25
    past
    0.25
    åĨįéĢł
    0.24
    Activations Density 0.937%

    No Known Activations