INDEX

Explanations

computer/technical text

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

à¸±à¸ĩ

-0.30

 cast

-0.29

 casting

-0.27

uyáº¿n

-0.27

Tau

-0.26

tau

-0.26

tau

-0.25

Tau

-0.24

¾

-0.24

ccount

-0.24

POSITIVE LOGITS

 exactly

0.28

publish

0.26

åħ¶æīĢ

0.24

åĩºä¼ļ

0.24

çĬ¬

0.24

å®ł

0.24

ä¹°çļĦ

0.24

 Solic

0.24

ped

0.23

Louis

0.23

Activations Density 0.002%

computer/technical text

No Comments

No Known Activations