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. 15-RESID-POST-AA
    6. 57036
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    鲔
    -0.07
    ใต
    -0.07
    车主
    -0.07
    桤
    -0.07
     boxes
    -0.07
    Ci
    -0.07
    Brown
    -0.06
    Coords
    -0.06
     freshwater
    -0.06
    学生
    -0.06
    POSITIVE LOGITS
    社会治理
    0.08
     umożliwia
    0.07
     TRACK
    0.07
     traitement
    0.07
    历史新高
    0.07
    anism
    0.07
    PRESSION
    0.07
    onitor
    0.07
     fraud
    0.07
     "`
    0.06
    Activations Density 0.010%

    No Known Activations