© 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. 15-RESID-POST-AA
    6. 119677
    Prev
    Next
    INDEX
    Explanations

    commercial

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     indebted
    -0.07
     lucky
    -0.07
     rés
    -0.07
     evade
    -0.06
    Leon
    -0.06
    ULLET
    -0.06
    計畫
    -0.06
    Φ
    -0.06
     canoe
    -0.06
     comparer
    -0.06
    POSITIVE LOGITS
     McG
    0.08
    文化产业
    0.08
    �
    0.07
    :CGRectMake
    0.07
    および
    0.07
    �
    0.07
    ymce
    0.07
    共和
    0.07
     kafka
    0.07
     حيث
    0.07
    Activations Density 0.042%

    No Known Activations