© 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. 23-TRANSCODER-HP
    7. 24888
    Prev
    Next
    INDEX
    Explanations

    override

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inh
    -0.27
    sworth
    -0.26
     perfect
    -0.26
    åħĥå·¦åı³
    -0.25
    erate
    -0.24
    abouts
    -0.24
    еÑĢж
    -0.24
    chnitt
    -0.24
    aday
    -0.24
    ä¾Ŀæ³ķ追究
    -0.24
    POSITIVE LOGITS
    çĤİ
    0.25
    tones
    0.25
     Blow
    0.25
     moreover
    0.24
    ä¹ĭä½ľ
    0.24
    иона
    0.24
    DM
    0.24
    .functional
    0.24
    .setAuto
    0.24
    ors
    0.24
    Activations Density 0.004%

    No Known Activations