© 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. 22-TRANSCODER-HP
    7. 87642
    Prev
    Next
    INDEX
    Explanations

    Website support/ad blocking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    бе
    -0.26
    çĶŁäº§çļĦ
    -0.25
    ifers
    -0.25
    åŁİå¸ĤçļĦ
    -0.24
     bog
    -0.24
     frustration
    -0.23
    çĺ«
    -0.23
    ç¼ł
    -0.23
     nug
    -0.23
    actus
    -0.23
    POSITIVE LOGITS
    ises
    0.29
    =yes
    0.27
    apist
    0.26
    imos
    0.26
    ken
    0.25
    ims
    0.24
    åĭĴ
    0.24
    zych
    0.24
     simul
    0.24
    æ·±å¤Ħ
    0.24
    Activations Density 0.032%

    No Known Activations