INDEX

Explanations

Unstructured data

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ÐºÑĢÑĥ

-0.26

_Ent

-0.25

 Clarence

-0.24

æĹĴ

-0.24

-scrollbar

-0.24

ï½ŀ↵↵

-0.24

è®¡

-0.23

æĸ¹å¼ıè¿Ľè¡Į

-0.23

 distributes

-0.23

é¢ļ

-0.23

POSITIVE LOGITS

 reproduction

0.30

 dial

0.27

 replication

0.27

athan

0.26

rett

0.25

 Dead

0.25

an

0.25

åĽŀå½Ĵ

0.25

 recreation

0.24

 production

0.24

Activations Density 0.004%

Unstructured data

No Comments

No Known Activations