© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 93049
    Prev
    Next
    INDEX
    Explanations

    Enemas or cleansing

    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
    _sphere
    -0.08
     �
    -0.07
    Lord
    -0.07
    Ѕ
    -0.07
    第三届
    -0.07
     Recover
    -0.06
     cyc
    -0.06
     truncated
    -0.06
    crud
    -0.06
     Nazis
    -0.06
    POSITIVE LOGITS
    AlgorithmException
    0.07
    儋
    0.07
    人为
    0.07
    UBL
    0.07
    beginTransaction
    0.07
    (IN
    0.07
    ée
    0.07
    랐
    0.07
    dır
    0.06
     оборуд
    0.06
    Activations Density 0.006%

    No Known Activations