INDEX

Explanations

Proper nouns, locations

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

æ¡£æ¬¡

-0.26

 sourcing

-0.25

acco

-0.24

psc

-0.24

 appet

-0.24

uppies

-0.24

apr

-0.23

 Manhattan

-0.23

å°ıæĹ¶åīį

-0.23

auga

-0.23

POSITIVE LOGITS

Fam

0.28

çŁľ

0.27

 familiar

0.26

è®¤çľŁåŃ¦ä¹ł

0.25

```

0.25

çĨŁæĤī

0.25

_OD

0.24

ÐµÐ´ÑĮ

0.24

Ãºs

0.24

sz

0.24

Activations Density 0.001%

Proper nouns, locations

No Comments

No Known Activations