© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 41972
    Prev
    Next
    INDEX
    Explanations

    model

    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
    ailand
    -0.07
    _running
    -0.07
    _sun
    -0.07
    拐
    -0.07
     distinguished
    -0.07
     「
    -0.07
    IFIED
    -0.07
    bob
    -0.07
    няя
    -0.07
    pine
    -0.07
    POSITIVE LOGITS
    .Measure
    0.08
     Putin
    0.07
    �
    0.07
    市场价格
    0.07
    ומות
    0.07
     Verse
    0.07
    观众
    0.07
    .matmul
    0.07
     uart
    0.07
    廒
    0.07
    Activations Density 0.017%

    No Known Activations