INDEX

Explanations

is

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æĹ¥æĻļ

-0.27

 flakes

-0.26

éľľ

-0.25

 Favor

-0.24

ç¹ģ

-0.24

 Ð¿Ð¾Ð´Ð´ÐµÑĢÐ¶Ð¸Ð²Ð°

-0.24

çłĶ

-0.24

Rog

-0.24

æĬ¬å¤´

-0.23

 favour

-0.23

POSITIVE LOGITS

éĢĨè½¬

0.28

ystack

0.28

uais

0.26

YSIS

0.25

-www

0.25

 reap

0.25

iasm

0.24

Ãºt

0.24

uales

0.24

åĬŃ

0.24

Activations Density 0.007%

is

No Comments

No Known Activations