© 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. 15-RESID-POST-AA
    11. 11077
    Prev
    Next
    INDEX
    Explanations

    Professions/Fields of study

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     TextInputType
    -0.08
    ��索
    -0.07
     trotz
    -0.07
     tiềm
    -0.07
    (MenuItem
    -0.07
    wear
    -0.07
    udes
    -0.07
    党的领导
    -0.07
    Nick
    -0.07
    ⚞
    -0.07
    POSITIVE LOGITS
     shakes
    0.07
     blast
    0.07
     estr
    0.07
    'u
    0.07
    0.06
    当场
    0.06
    ⼋
    0.06
     bin
    0.06
     UA
    0.06
    ණ
    0.06
    Activations Density 0.071%

    No Known Activations