Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 2190
    Prev
    Next
    INDEX
    Explanations

    9

    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
     Fuk
    -0.07
    .rdf
    -0.07
    figures
    -0.07
     dozen
    -0.07
     disillusion
    -0.07
     dudes
    -0.07
    习近平新
    -0.07
     Yup
    -0.07
    ulner
    -0.07
     בשנים
    -0.07
    POSITIVE LOGITS
    amiento
    0.07
    current
    0.07
     INTER
    0.07
    欧元
    0.07
    管理中心
    0.07
    皮肤
    0.07
    Coordinate
    0.07
     Joint
    0.07
    freeze
    0.06
     Ops
    0.06
    Activations Density 0.029%

    No Known Activations