© 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. 127352
    Prev
    Next
    INDEX
    Explanations

    Tilda Swinton

    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
     dash
    -0.07
     oa
    -0.07
    怼
    -0.07
    ⟳
    -0.07
     extracting
    -0.07
    .ToolStripItem
    -0.07
    Override
    -0.07
     restrictive
    -0.07
     nostalgia
    -0.07
     defensively
    -0.07
    POSITIVE LOGITS
    的心理
    0.08
    _CM
    0.07
    鼫
    0.07
    𝘁
    0.07
     Camden
    0.07
     Phelps
    0.07
    BEST
    0.07
    կ
    0.06
     Angel
    0.06
     An
    0.06
    Activations Density 0.029%

    No Known Activations