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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 7-RESID-POST-AA
    11. 59309
    Prev
    Next
    INDEX
    Explanations

    County

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    有效
    -0.07
    🤍
    -0.07
    充分
    -0.07
    任性
    -0.07
    执着
    -0.07
     Seventh
    -0.07
    耐磨
    -0.07
    保证
    -0.06
     eclectic
    -0.06
    为代表的
    -0.06
    POSITIVE LOGITS
    cen
    0.07
    кал
    0.07
    шин
    0.07
    ߓ
    0.07
    fsp
    0.07
    ا�
    0.07
     subdiv
    0.07
    �
    0.07
    ציג
    0.07
    prite
    0.07
    Activations Density 0.008%

    No Known Activations