© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 68992
    Prev
    Next
    INDEX
    Explanations

    viewport

    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
    .addNode
    -0.07
    _MIC
    -0.07
    .HE
    -0.07
    捋
    -0.07
    缒
    -0.07
    PathComponent
    -0.07
     tiger
    -0.07
    .switch
    -0.07
     никак
    -0.07
    ,:,
    -0.07
    POSITIVE LOGITS
    _par
    0.08
     Üniversitesi
    0.07
    镩
    0.07
     rebuilt
    0.07
    铜
    0.07
     resilience
    0.07
    랔
    0.07
    �
    0.07
    orthy
    0.07
    eneration
    0.07
    Activations Density 0.001%

    No Known Activations