INDEX

Explanations

Names

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ķĮ

-0.38

æĪª

-0.35

 pant

-0.31

çĶ«

-0.28

ign

-0.28

 station

-0.26

 eins

-0.26

orca

-0.25

çĦ°

-0.24

 engr

-0.24

POSITIVE LOGITS

ì§ĳ

0.25

 Grants

0.25

ë£©

0.25

-shared

0.25

esto

0.25

airs

0.24

 anywhere

0.24

setParameter

0.23

CIA

0.23

alties

0.23

Activations Density 0.784%

Names

No Comments

No Known Activations