INDEX

Explanations

scientific and medical texts

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_33.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.33.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 laser

-0.26

 Laser

-0.25

çĤĴ

-0.25

 Volley

-0.25

esser

-0.24

onitor

-0.23

Ĥ¤

-0.23

Sharper

-0.23

 Street

-0.23

 TInt

-0.23

POSITIVE LOGITS

 negative

0.29

ä½©

0.29

è´Ł

0.28

ILT

0.28

çĶŁçī©

0.27

 causal

0.26

 biomedical

0.25

èį¯ä¸ļ

0.25

 biology

0.25

_Inter

0.25

Activations Density 0.013%

scientific and medical texts

No Comments

No Known Activations