© 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. 23277
    Prev
    Next
    INDEX
    Explanations

    time

    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
     scary
    -0.07
    _and
    -0.07
    Ѩ
    -0.07
     USSR
    -0.07
    ∾
    -0.07
    医疗
    -0.07
     };
    -0.06
    _view
    -0.06
     explore
    -0.06
    ỏ
    -0.06
    POSITIVE LOGITS
     Secondly
    0.07
     Hak
    0.07
    orus
    0.07
     magna
    0.06
     Gust
    0.06
     Shaft
    0.06
     Before
    0.06
     Returning
    0.06
    门户
    0.06
    电量
    0.06
    Activations Density 0.130%

    No Known Activations