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. 35935
    Prev
    Next
    INDEX
    Explanations

    books

    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
     phát
    -0.07
    冀
    -0.07
     ngủ
    -0.06
    .Look
    -0.06
     él
    -0.06
     เมษายน
    -0.06
    (inv
    -0.06
    ⮟
    -0.06
     рем
    -0.06
     télé
    -0.06
    POSITIVE LOGITS
     wildcard
    0.07
    Ultra
    0.07
     rude
    0.06
    破产
    0.06
    UND
    0.06
    otypical
    0.06
    xed
    0.06
    石材
    0.06
     rugged
    0.06
    产业基地
    0.06
    Activations Density 0.054%

    No Known Activations