© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 107125
    Prev
    Next
    INDEX
    Explanations

    Code-related texts

    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
    Negative Logits
    yms
    -0.28
     ÑĢÑıд
    -0.26
    imate
    -0.26
    åįĴ
    -0.25
    Selectors
    -0.25
    ride
    -0.25
    åĴĮæĶ¯æĮģ
    -0.24
     Rand
    -0.24
     rien
    -0.24
    otal
    -0.24
    POSITIVE LOGITS
    æĸĻ
    0.29
    èĴ¹
    0.29
     bureaucr
    0.28
    AGR
    0.26
    mist
    0.25
    èįīåİŁ
    0.25
    antha
    0.25
    çĶŁæĢģåľĪ
    0.24
    dana
    0.24
     libertine
    0.24
    Activations Density 0.154%

    No Known Activations