INDEX

Explanations

Medical terminology/procedures

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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

 astro

-0.27

ference

-0.27

loy

-0.26

unf

-0.24

dig

-0.24

_assigned

-0.24

estic

-0.24

param

-0.23

_refer

-0.23

pons

-0.23

POSITIVE LOGITS

-derived

0.28

èĲ¥

0.27

derived

0.26

 derived

0.26

inance

0.25

essages

0.24

 segue

0.24

 nameof

0.24

orf

0.24

 perpetual

0.24

Activations Density 0.113%

Medical terminology/procedures

No Comments

No Known Activations