© 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. 12-TRANSCODER-HP
    7. 23042
    Prev
    Next
    INDEX
    Explanations

    off

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    loff
    -0.29
    æĥ¯
    -0.27
    dish
    -0.27
    _Read
    -0.25
    tabs
    -0.25
    伸æīĭ
    -0.24
     off
    -0.24
     RID
    -0.24
    uja
    -0.24
    reads
    -0.24
    POSITIVE LOGITS
    atem
    0.26
     atom
    0.26
    atom
    0.26
    rvine
    0.25
    ents
    0.25
    èĥ±
    0.25
    éĢļçķħ
    0.24
    ctime
    0.24
    ater
    0.24
     alignments
    0.24
    Activations Density 0.123%

    No Known Activations