© 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. 11-RESID-POST-AA
    11. 22724
    Prev
    Next
    INDEX
    Explanations

    against

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ado
    -0.08
     настоящее
    -0.07
    דרך
    -0.07
    楼下
    -0.07
    חה
    -0.07
     aun
    -0.07
    以人民为
    -0.07
    OMB
    -0.07
     Ack
    -0.07
    enic
    -0.07
    POSITIVE LOGITS
    +z
    0.08
    height
    0.07
     akt
    0.07
     persu
    0.07
    헸
    0.07
    醚
    0.07
     buckle
    0.07
    ティ
    0.06
    能力
    0.06
     eventType
    0.06
    Activations Density 0.062%

    No Known Activations