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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 2380
    Prev
    Next
    INDEX
    Explanations

    section/subsection

    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
     camper
    -0.07
    .cd
    -0.07
    -existing
    -0.07
     Pump
    -0.07
     brave
    -0.07
    oper
    -0.07
    六
    -0.06
     stranger
    -0.06
    cre
    -0.06
    DET
    -0.06
    POSITIVE LOGITS
     grues
    0.08
    国立
    0.07
    른
    0.07
     Berlin
    0.07
    מראה
    0.07
     그것
    0.07
    챤
    0.07
    ировка
    0.07
    欧阳
    0.07
    .setLayout
    0.06
    Activations Density 0.001%

    No Known Activations