INDEX

Explanations

functions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

bilt

-0.28

 reconciliation

-0.26

^K

-0.25

enes

-0.25

conda

-0.25

conciliation

-0.24

 Wilkinson

-0.24

tex

-0.24

(dep

-0.24

 Round

-0.23

POSITIVE LOGITS

.cgi

0.28

 ::↵

0.28

Cah

0.27

::↵

0.27

chy

0.26

ughty

0.26

ouch

0.26

ALAR

0.25

deaux

0.25

åıĳæī¬

0.25

Activations Density 0.010%

functions

No Comments

No Known Activations