© 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. 33-TRANSCODER-HP
    7. 53228
    Prev
    Next
    INDEX
    Explanations

    parts of words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æī«
    -0.28
     spr
    -0.25
    åĪį
    -0.25
    haft
    -0.24
    иÑħ
    -0.24
    åķ¬
    -0.24
    /html
    -0.24
    leg
    -0.23
     titles
    -0.23
    alted
    -0.23
    POSITIVE LOGITS
    mos
    0.30
     roma
    0.26
    bag
    0.25
    mess
    0.25
    fi
    0.24
    pth
    0.24
    poke
    0.24
    没åĬŀæ³ķ
    0.24
    bio
    0.24
    oki
    0.23
    Activations Density 0.005%

    No Known Activations