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. 7684
    Prev
    Next
    INDEX
    Explanations

    -plugin

    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
     destinationViewController
    -0.07
    旁边的
    -0.07
    TING
    -0.07
     hans
    -0.06
     wedding
    -0.06
    倓
    -0.06
    oeff
    -0.06
     phúc
    -0.06
     disproportionately
    -0.06
    颞
    -0.06
    POSITIVE LOGITS
    gressor
    0.08
    :name
    0.07
    Recorder
    0.07
     Maker
    0.07
    .Iterator
    0.07
    Selected
    0.07
    猴
    0.07
    outube
    0.07
    ItemClickListener
    0.07
    (Index
    0.07
    Activations Density 0.004%

    No Known Activations