INDEX

Explanations

scientific texts

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

onor

-0.28

 hands

-0.28

ponsored

-0.26

ä¹ĭä¹¡

-0.26

åĬ¨æīĭ

-0.26

åı£å¾Ħ

-0.24

ExecutionContext

-0.24

ields

-0.23

ated

-0.23

 Hands

-0.23

POSITIVE LOGITS

 curt

0.30

chal

0.28

è¿Ļå°±æĺ¯

0.28

ç´¯äºĨ

0.28

å¾Ģä¸Ĭ

0.27

icing

0.26

drawing

0.26

emics

0.25

åĴ¯

0.25

alach

0.25

Activations Density 0.017%

scientific texts

No Comments

No Known Activations