INDEX

Explanations

auxiliary verbs

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

 Casual

-0.25

|#

-0.24

 seating

-0.24

tik

-0.24

 seat

-0.24

 tert

-0.23

 subdiv

-0.23

 especÃŃfico

-0.23

åĽłåľ°

-0.23

åº¦

-0.23

POSITIVE LOGITS

oved

0.29

åŀĴ

0.27

_managed

0.27

sez

0.25

fo

0.25

è®®åĳĺ

0.25

elta

0.24

StackTrace

0.24

calar

0.24

 skyline

0.24

Activations Density 0.004%

auxiliary verbs

No Comments

No Known Activations