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. 49799
    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
     TNT
    -0.07
     Ank
    -0.07
    -bound
    -0.06
     Cotton
    -0.06
    上下
    -0.06
    不变
    -0.06
    venient
    -0.06
    人大代表
    -0.06
    应付
    -0.06
    络
    -0.06
    POSITIVE LOGITS
    qid
    0.08
     crippling
    0.07
    体系建设
    0.07
     facilit
    0.07
     Definitions
    0.06
     Parser
    0.06
    .ITEM
    0.06
    三年
    0.06
     cm
    0.06
    AMPLE
    0.06
    Activations Density 0.030%

    No Known Activations