© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 110726
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    𤧛
    -0.07
    普法
    -0.07
    𝚖
    -0.06
    椪
    -0.06
    .AspNetCore
    -0.06
     Taco
    -0.06
    ("(%
    -0.06
    êu
    -0.06
    脱贫攻坚
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     cut
    0.07
     sisters
    0.07
    Fall
    0.06
    concat
    0.06
     bundle
    0.06
    .format
    0.06
     matches
    0.06
    asury
    0.06
     CONTROL
    0.06
    ",
    ↵
    0.06
    Activations Density 0.003%

    No Known Activations