© 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. 108359
    Prev
    Next
    INDEX
    Explanations

    to or

    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
    åħ¶ä»ĸåĽ½å®¶
    -0.27
     disagreements
    -0.26
    åħ¶ä»ĸ人
    -0.26
     disagreement
    -0.26
    åĪĨæѧ
    -0.25
    次ä¼ļè®®
    -0.25
    chè
    -0.25
     theirs
    -0.25
    éĺ²çĽĹ
    -0.23
    emoth
    -0.23
    POSITIVE LOGITS
    ernal
    0.28
    _pin
    0.28
    Pin
    0.26
    ulatory
    0.26
    _stderr
    0.25
     QDir
    0.25
    åŁł
    0.25
    ozo
    0.24
    _tokenize
    0.24
    çĸĿ
    0.24
    Activations Density 0.122%

    No Known Activations