INDEX

Explanations

prepositions

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_18.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.18.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

èĥ½

-0.28

antic

-0.26

èī¯æĢ§

-0.26

able

-0.25

lage

-0.24

ç®Ĺ

-0.24

æĺ¯åı¯ä»¥

-0.24

ä¸įä½ı

-0.23

bury

-0.23

antium

-0.23

POSITIVE LOGITS

isode

0.28

_same

0.24

Same

0.23

neau

0.23

uD

0.23

 Ð¼Ð°

0.22

Refer

0.22

ourcing

0.22

setLayout

0.22

èį¦

0.22

Activations Density 50.430%

prepositions

No Comments

No Known Activations