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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 19-RESID-POST-AA
    11. 109645
    Prev
    Next
    INDEX
    Explanations

    code branching logic

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (F
    -0.07
    ❅
    -0.07
    [ind
    -0.07
     meaningless
    -0.07
    脈
    -0.07
     Setup
    -0.07
     words
    -0.07
    的样子
    -0.07
    Ini
    -0.07
     graduated
    -0.06
    POSITIVE LOGITS
    getMock
    0.07
    _CBC
    0.06
    FD
    0.06
    _reporting
    0.06
     ROT
    0.06
    핌
    0.06
    底盘
    0.06
     Investor
    0.06
     Merch
    0.06
    .getError
    0.06
    Activations Density 0.029%

    No Known Activations