INDEX

Explanations

port

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

åĩĢ

-0.30

argin

-0.28

_UL

-0.26

antha

-0.26

mgr

-0.26

 convoy

-0.26

çļĦæĥħ

-0.24

rams

-0.24

 manned

-0.24

IMIT

-0.24

POSITIVE LOGITS

logic

0.31

æ³ķåĪĻ

0.29

 jail

0.28

 logic

0.28

 jails

0.27

çĥĻ

0.26

pla

0.26

stra

0.25

 SCAN

0.25

 poll

0.25

Activations Density 0.007%

port

No Comments

No Known Activations