Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 35706
    Prev
    Next
    INDEX
    Explanations

    uary

    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
    индивиду
    -0.07
     superb
    -0.07
    Mis
    -0.07
    �
    -0.06
    los
    -0.06
    _TM
    -0.06
     והמ
    -0.06
    outh
    -0.06
     Chun
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    <Scalar
    0.09
    <vector
    0.07
    _beh
    0.06
    طق
    0.06
    =dict
    0.06
     akş
    0.06
     }}
    0.06
    个工作
    0.06
    dojo
    0.06
    ."""
    0.06
    Activations Density 0.066%

    No Known Activations