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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 110167
    Prev
    Next
    INDEX
    Explanations

    Economic stimulus and policy

    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
    儿
    -0.08
    canf
    -0.07
    兒
    -0.07
    /foo
    -0.07
    OMUX
    -0.06
     yak
    -0.06
     Universe
    -0.06
     meis
    -0.06
    ར
    -0.06
     دول
    -0.06
    POSITIVE LOGITS
    Fetcher
    0.07
    分からない
    0.07
    hunt
    0.07
    欲しい
    0.07
    琔
    0.07
     Percy
    0.07
    cursor
    0.07
    ᵑ
    0.07
    分布在
    0.07
    膝盖
    0.07
    Activations Density 0.026%

    No Known Activations