© 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. 22018
    Prev
    Next
    INDEX
    Explanations

    business functions

    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
    .Virtual
    -0.08
    ERVED
    -0.07
    Gratis
    -0.07
    .documents
    -0.06
    .numericUpDown
    -0.06
    (selection
    -0.06
     ctypes
    -0.06
    確保
    -0.06
    筏
    -0.06
    オン
    -0.06
    POSITIVE LOGITS
     Ди
    0.08
     strong
    0.07
    反而
    0.07
     ­
    0.07
    -,
    0.07
    考え方
    0.07
    JWT
    0.07
    AccessException
    0.07
     Require
    0.07
    ເ
    0.07
    Activations Density 0.091%

    No Known Activations