© 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. 39559
    Prev
    Next
    INDEX
    Explanations

    boundary

    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
    �
    -0.08
     tả
    -0.07
     narcotics
    -0.07
    整
    -0.07
    毀
    -0.07
    閱
    -0.07
    🕗
    -0.07
    fc
    -0.07
     tolerate
    -0.07
    lec
    -0.07
    POSITIVE LOGITS
     boundary
    0.08
     Boundary
    0.08
    atories
    0.07
    .single
    0.07
    든지
    0.07
    边界
    0.07
     carefully
    0.07
     hinge
    0.07
    中心
    0.07
     outputFile
    0.07
    Activations Density 0.007%

    No Known Activations