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. 15-RESID-POST-AA
    6. 120953
    Prev
    Next
    INDEX
    Explanations

    Patents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fear
    -0.08
     אוה
    -0.07
     paternal
    -0.07
    _refresh
    -0.07
     Pendant
    -0.07
     Ply
    -0.07
     Clover
    -0.07
    県
    -0.07
    Explorer
    -0.07
    杓
    -0.07
    POSITIVE LOGITS
    sets
    0.08
     spaces
    0.08
     thus
    0.07
    partials
    0.07
     Wiley
    0.07
    思
    0.07
    數
    0.06
    assume
    0.06
    慰
    0.06
    ToList
    0.06
    Activations Density 0.078%

    No Known Activations