© 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. 625
    Prev
    Next
    INDEX
    Explanations

    Time and date

    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_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
     bigger
    -0.07
    良い
    -0.07
    publisher
    -0.07
    �
    -0.07
    因此
    -0.07
     convin
    -0.07
     marks
    -0.07
    �
    -0.07
    新疆
    -0.07
    准确
    -0.07
    POSITIVE LOGITS
     OpCode
    0.08
     Gesture
    0.07
    烬
    0.07
     Registers
    0.07
    .SceneManagement
    0.07
    玞
    0.07
     graveyard
    0.07
     "`
    0.07
     hurd
    0.07
    .Nodes
    0.07
    Activations Density 0.025%

    No Known Activations