© 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. 58344
    Prev
    Next
    INDEX
    Explanations

    code and file paths

    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
    Not in Any Lists

    No Comments

    Negative Logits
    çĥ
    -0.27
    orn
    -0.26
    ideo
    -0.25
     running
    -0.25
    满
    -0.25
    steam
    -0.24
     infiltr
    -0.24
    ormap
    -0.24
     def
    -0.24
     mounting
    -0.24
    POSITIVE LOGITS
    ocity
    0.27
    éĢĬ
    0.27
     knobs
    0.25
    å¾Ĺèµ·
    0.25
    berger
    0.25
     Reco
    0.25
    -Ray
    0.25
    enson
    0.25
    ifier
    0.25
    rey
    0.25
    Activations Density 0.002%

    No Known Activations