© 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. 15-RESID-POST-AA
    11. 129169
    Prev
    Next
    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash
    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
    ϓ
    -0.07
    ield
    -0.07
    aption
    -0.07
    马来西亚
    -0.06
    .sponge
    -0.06
    搪
    -0.06
    �
    -0.06
    区块链
    -0.06
    .encode
    -0.06
     bound
    -0.06
    POSITIVE LOGITS
     whit
    0.07
    InOut
    0.07
    @Web
    0.07
    娃娃
    0.07
     Quiz
    0.07
    证券
    0.07
     XCTest
    0.07
    西洋
    0.07
    润滑
    0.07
    _secs
    0.06
    Activations Density 0.022%

    No Known Activations