INDEX

Explanations

in

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_19.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.19.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

äº²è¿ĳ

-0.26

 grounds

-0.25

.Atomic

-0.25

mapper

-0.25

å«ģç»Ļ

-0.25

OURSE

-0.24

å°ģéĶģ

-0.24

ind

-0.24

(SIG

-0.24

etto

-0.24

POSITIVE LOGITS

orc

0.29

äººæ°Ķ

0.27

parer

0.27

reds

0.25

 facult

0.25

Elk

0.24

tur

0.24

é©¿

0.24

 concess

0.23

Ø¶

0.23

Activations Density 0.031%

in

No Comments

No Known Activations