© 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 EvalsExportsAPI 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. 70248
    Prev
    Next
    INDEX
    Explanations

    mechanical

    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
     kısmı
    -0.09
    今天的
    -0.08
     Cue
    -0.08
    vos
    -0.07
    Editar
    -0.07
    nama
    -0.07
    esthesia
    -0.07
    ď
    -0.07
    宁波
    -0.07
    upp
    -0.07
    POSITIVE LOGITS
     mechanical
    0.08
    𝖓
    0.07
    benef
    0.07
     trivial
    0.07
     {}.
    0.07
    土壤
    0.07
    要去
    0.06
     challenger
    0.06
     bound
    0.06
    概率
    0.06
    Activations Density 0.013%

    No Known Activations