INDEX

Explanations

instruments

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

åĲĦåĮº

-0.30

åĨ³

-0.26

åıĸ

-0.26

åĪĨ

-0.26

èĢħ

-0.26

 limp

-0.25

åįıè°ĥ

-0.24

older

-0.24

æĭ¯

-0.24

ereo

-0.24

POSITIVE LOGITS

EMBER

0.27

 Caval

0.26

 Borg

0.25

axe

0.25

_BOOLEAN

0.24

 figur

0.24

 GENER

0.24

Ax

0.24

plr

0.24

GENER

0.23

Activations Density 0.001%

instruments

No Comments

No Known Activations