© 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. 107515
    Prev
    Next
    INDEX
    Explanations

    Technical documentation snippets

    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
     Favor
    -0.28
    -Men
    -0.25
     DAMAGE
    -0.25
    åį¯
    -0.25
    åij½ä¸Ń
    -0.24
     pro
    -0.24
    æŁ¥çľĭ详æĥħ
    -0.24
     Mine
    -0.24
     tô
    -0.23
    çĮĽ
    -0.23
    POSITIVE LOGITS
    asaki
    0.29
    å®Ľ
    0.27
    icular
    0.27
    çľĭä¼¼
    0.26
    èµ°åİ»
    0.25
    å³Ļ
    0.25
     STRUCT
    0.24
    黯
    0.24
    ax
    0.24
    åѤçĭ¬
    0.24
    Activations Density 0.020%

    No Known Activations