INDEX

Explanations

Chemistry/Spectroscopy/NMR

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

éºĵ

-0.29

ELS

-0.28

idis

-0.28

èĢģé¼ł

-0.28

eling

-0.27

 RAND

-0.26

uder

-0.25

.detach

-0.25

æī¹éĩı

-0.25

 pand

-0.25

POSITIVE LOGITS

 reflection

0.28

åĲ¸æĶ¶

0.27

rastructure

0.27

achi

0.27

éĻª

0.27

Reflection

0.26

åĪĨæĺİ

0.26

 Reflection

0.26

çĽ¸å¹²

0.26

 operated

0.25

Activations Density 0.106%

Chemistry/Spectroscopy/NMR

No Comments

No Known Activations