INDEX

Explanations

scientific/medical research

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_33.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.33.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 mxArray

-0.27

neys

-0.27

Ire

-0.26

heim

-0.26

anchors

-0.25

ije

-0.25

iments

-0.24

.Transactional

-0.24

_txn

-0.24

èµŀèµı

-0.24

POSITIVE LOGITS

éķĽ

0.29

pan

0.28

 banda

0.27

pan

0.26

Pan

0.26

 naive

0.26

 Band

0.26

 band

0.26

built

0.26

log

0.25

Activations Density 0.701%

scientific/medical research

No Known Activations