© 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. 23-RESID-POST-AA
    11. 129960
    Prev
    Next
    INDEX
    Explanations

    legal and court related

    np_max-act-logits · gemini-2.0-flashTriggered by @majianfei030706
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tackling
    -0.07
    賦
    -0.06
    Elements
    -0.06
    Comput
    -0.06
    capitalize
    -0.06
    Published
    -0.06
    Whether
    -0.06
    Leon
    -0.06
    发布时间
    -0.06
    美国总统
    -0.06
    POSITIVE LOGITS
    =result
    0.07
     square
    0.07
     FORMAT
    0.07
     userManager
    0.07
    普通的
    0.07
    upakan
    0.07
     EQUI
    0.06
    _observer
    0.06
     Median
    0.06
     Mode
    0.06
    Activations Density 0.015%

    No Known Activations