INDEX

Explanations

ical

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

VOL

-0.28

ammers

-0.28

Vol

-0.27

/lgpl

-0.26

 Hera

-0.26

azio

-0.25

åĨ²

-0.25

ur

-0.25

{n

-0.25

ur

-0.25

POSITIVE LOGITS

çĻ½æĸĳ

0.28

æķĽ

0.26

äººéĻħåħ³ç³»

0.26

 depress

0.26

 Investig

0.26

æī¼

0.26

hil

0.26

 sustained

0.25

èĤĮ

0.25

hill

0.25

Activations Density 0.040%

ical

No Comments

No Known Activations