© 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. 27-TRANSCODER-HP
    7. 9872
    Prev
    Next
    INDEX
    Explanations

    hom words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    第äºĶå±Ĭ
    -0.30
    产ä¸ļç»ĵæŀĦ
    -0.28
    ural
    -0.27
    uality
    -0.27
    ç¬¬åĽĽå±Ĭ
    -0.27
    urally
    -0.26
    BERS
    -0.26
    ted
    -0.26
    å±Ģ
    -0.25
    管çIJĨå±Ģ
    -0.25
    POSITIVE LOGITS
    edes
    0.31
     generic
    0.27
     Generic
    0.26
    è´²
    0.26
    Suppress
    0.25
    Generic
    0.25
     comp
    0.24
    黡
    0.24
     force
    0.23
    crit
    0.23
    Activations Density 0.001%

    No Known Activations