© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 2201
    Prev
    Next
    INDEX
    Explanations

    or

    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
    酂
    -0.09
     Mons
    -0.07
    _mpi
    -0.07
     Funk
    -0.07
    Invariant
    -0.07
    心理学
    -0.07
    舆
    -0.06
    Unix
    -0.06
    焊
    -0.06
     воз
    -0.06
    POSITIVE LOGITS
    喜好
    0.08
    ⾃
    0.07
     ALLOW
    0.07
    arrêt
    0.07
    急于
    0.07
    的事情
    0.07
    description
    0.07
    choices
    0.07
    ально
    0.07
     tak
    0.07
    Activations Density 0.012%

    No Known Activations