© 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. 24756
    Prev
    Next
    INDEX
    Explanations

    Thinking, possibility

    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
    çĤŃ
    -0.26
    chaft
    -0.26
    lite
    -0.25
    usher
    -0.25
    æľº
    -0.25
    éĴĵé±¼
    -0.25
    odable
    -0.25
    使æĪij
    -0.24
    æĦŁ
    -0.24
    forge
    -0.24
    POSITIVE LOGITS
     naw
    0.27
    è¿ľå¤Ħ
    0.27
    ighb
    0.26
    aset
    0.26
     pseud
    0.25
    åİŁå§ĭ
    0.24
    èŀ«
    0.24
    erior
    0.24
    'name
    0.24
    importe
    0.24
    Activations Density 0.003%

    No Known Activations