© 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. 27-TRANSCODER-HP
    7. 57786
    Prev
    Next
    INDEX
    Explanations

    technical texts

    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
    Computed
    -0.27
    dig
    -0.27
     Computing
    -0.26
    èĤł
    -0.26
    æĥ¬
    -0.26
    icter
    -0.25
     natuur
    -0.25
     Burns
    -0.24
    interopRequire
    -0.24
     COMPUT
    -0.23
    POSITIVE LOGITS
    osoph
    0.31
    çĿ½
    0.28
    _globals
    0.26
    truth
    0.25
     profes
    0.25
     cab
    0.25
    Truth
    0.24
     covered
    0.24
    åĽŀæĶ¶
    0.24
    åĽ´çĿĢ
    0.24
    Activations Density 0.000%

    No Known Activations