© 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. 25-TRANSCODER-HP
    7. 107812
    Prev
    Next
    INDEX
    Explanations

    not

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    prise
    -0.26
     Uncomment
    -0.25
    ise
    -0.25
    itez
    -0.25
     Later
    -0.24
    lox
    -0.24
    rades
    -0.24
    yat
    -0.24
    eeper
    -0.23
    å°Ĩè¾¾åĪ°
    -0.23
    POSITIVE LOGITS
    зв
    0.25
    è¿ĩäºİ
    0.25
    缴
    0.24
    åį·
    0.24
    ercul
    0.24
    _timing
    0.24
    åľ°äº§
    0.23
    esium
    0.23
     proc
    0.23
    VP
    0.23
    Activations Density 0.988%

    No Known Activations