INDEX

Explanations

Acronyms and initialisms

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

eof

-0.31

èį¡

-0.29

æĤ¬

-0.28

rowCount

-0.26

é¼ĵ

-0.25

æĺİçĻ½

-0.25

athom

-0.25

:].

-0.24

.mit

-0.24

adol

-0.24

POSITIVE LOGITS

è·ĸ

0.28

ä¸ĩèĤ¡

0.25

 litres

0.24

 convergence

0.24

 Complex

0.24

è·¯çº¿

0.24

verse

0.23

ëł¨

0.23

 tallest

0.23

èĹķ

0.23

Activations Density 23.039%

Acronyms and initialisms

No Comments

No Known Activations