INDEX

Explanations

the

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

anken

-0.28

antor

-0.26

 plane

-0.25

è¿ĶåĽŀæĲľçĭĲ

-0.24

 sideline

-0.24

 porta

-0.24

 Ð´Ð¾Ð±ÑĢÐ¾

-0.24

Ð±Ð¾

-0.24

ä¸Ģç±»

-0.24

ä¿±

-0.24

POSITIVE LOGITS

å¥¹æĺ¯

0.26

ŀæĢ§

0.25

 Frau

0.25

åĽ½äºº

0.25

 kÃª

0.24

.execution

0.24

 earned

0.24

æīĵåħ¥

0.23

HeaderView

0.23

çĲĨè§£åĴĮ

0.23

Activations Density 0.000%

the

No Comments

No Known Activations