© 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. 456
    Prev
    Next
    INDEX
    Explanations

    Disasters and acts of God

    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
    _Tool
    -0.07
    igan
    -0.07
    一个问题
    -0.07
    Monitoring
    -0.07
    igious
    -0.06
    Directions
    -0.06
    籴
    -0.06
    诮
    -0.06
    枘
    -0.06
    inan
    -0.06
    POSITIVE LOGITS
    orderid
    0.07
    阻力
    0.07
    的身份
    0.07
     Capacity
    0.06
     Reliable
    0.06
     kontakte
    0.06
    С
    0.06
    .has
    0.06
    阿根廷
    0.06
    所产生的
    0.06
    Activations Density 0.002%

    No Known Activations