INDEX

Explanations

scientific texts

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

day

-0.30

Day

-0.30

Day

-0.27

hold

-0.27

ÃŃc

-0.27

ctors

-0.26

day

-0.26

Holder

-0.26

cond

-0.25

 bund

-0.25

POSITIVE LOGITS

kah

0.27

jabi

0.27

è¦ģç´§

0.26

avax

0.25

kho

0.25

gmt

0.25

ç»Īç»ĵ

0.24

 independence

0.24

åĲĪçĲĨ

0.23

sci

0.23

Activations Density 0.019%

scientific texts

No Comments

No Known Activations